Daily Papers

Self-evolving agents turn experience into reusable skills, workflows, or memories, but post-evolution accuracy alone does not show whether learned behavior preserves previously correct behavior or security. We audit SkillOpt, Agent Workflow Memory (AWM), and ReasoningBank in simulated e-banking using matched benign acquisition trajectories, sealed evaluation endpoints, execution-grounded checks, and independent state replay. On Qwen 3.7 Flash, SkillOpt raises benign utility from 0.741 to 0.837 while exposure to injected content rises from 0.820 to 0.943. Conditional attack success after exposure falls from 0.605 to 0.562, yet overall attack success rate (ASR) rises from 0.496 to 0.530 and unauthorized financial state changes rise to 0.685. Across three independently evolved lineages, capability, exposure, and unauthorized-state changes increase in all three, whereas ASR increases in only two. ReasoningBank raises utility to 0.859 without increasing aggregate ASR, although unauthorized state changes remain slightly above Static. AWM reveals a separate evaluation hazard: a literal WebArena text-action envelope disrupts tool execution in our native function-calling executor. In a post-hoc sensitivity test, removing only that envelope restores utility from 0.319 to 0.756, while exposure rises from 0.299 to 0.909 and ASR from 0.195 to 0.575. Auditing self-evolving financial agents therefore requires tracking regressions, attack-surface contact, unauthorized financial-state change, and artifact-executor compatibility, not accuracy alone.

Long-horizon tool agents often make useful progress without reaching terminal success, motivating partial-credit evaluation. Yet evaluators may reward milestones that were temporary, later reversed, or not attributable to the evaluated agent. Comparing an honest trajectory with a higher-scoring adversarial one is inconclusive if the latter made more genuine progress. We introduce PartHackBench, a controlled methodology that removes this confound. A private certifier admits a pair only when its trajectories match component-wise in both current-state predicate satisfaction and standardized agent attribution; score inflation, defined as f(A) - f(H), is measured only afterward. In 18 sealed held-out tasks in PB-CSTE, the frozen historical-target run produced matched adversaries for 15 tasks. Historical credit yielded mean inflation of .252, conditional attack success of 10/15, end-to-end yield of 10/18, and detected none of 14 strict rollbacks. Semantic LLM judges were more resistant but remained vulnerable, especially under evaluator-targeted attacks, while PB-CSTE current-state controls, defined as exact functions of the certified components, yielded zero inflation by construction. PartHackBench thus provides a certified control for testing whether evaluator credit changes while all benchmark-defined task-relevant progress remains fixed.

The rise of Omni-modal Large Language Models (OLLMs), which integrate visual and auditory processing with text, necessitates robust safety evaluations to mitigate harmful outputs. However, no dedicated benchmarks currently exist for OLLMs, and prior benchmarks designed for other LLMs lack the ability to assess safety performance under audio-visual joint inputs or cross-modal safety consistency. To fill this gap, we introduce Omni-SafetyBench, the first comprehensive parallel benchmark for OLLM safety evaluation, featuring 24 modality combinations and variations with 972 samples each, including dedicated audio-visual harm cases. Considering OLLMs' comprehension challenges with complex omni-modal inputs and the need for cross-modal consistency evaluation, we propose tailored metrics: a Safety-score based on conditional Attack Success Rate (C-ASR) and Refusal Rate (C-RR) to account for comprehension failures, and a Cross-Modal Safety Consistency Score (CMSC-score) to measure consistency across modalities. Evaluating 6 open-source and 4 closed-source OLLMs reveals critical vulnerabilities: (1) no model excels in both overall safety and consistency, with only 3 models achieving over 0.6 in both metrics and top performer scoring around 0.8; (2) safety defenses weaken with complex inputs, especially audio-visual joints; (3) severe weaknesses persist, with some models scoring as low as 0.14 on specific modalities. Our benchmark and metrics highlight urgent needs for enhanced OLLM safety, providing a foundation for future improvements.

Model inversion (MI) attacks have raised increasing concerns about privacy, which can reconstruct training data from public models. Indeed, MI attacks can be formalized as an optimization problem that seeks private data in a certain space. Recent MI attacks leverage a generative adversarial network (GAN) as an image prior to narrow the search space, and can successfully reconstruct even the high-dimensional data (e.g., face images). However, these generative MI attacks do not fully exploit the potential capabilities of the target model, still leading to a vague and coupled search space, i.e., different classes of images are coupled in the search space. Besides, the widely used cross-entropy loss in these attacks suffers from gradient vanishing. To address these problems, we propose Pseudo Label-Guided MI (PLG-MI) attack via conditional GAN (cGAN). At first, a top-n selection strategy is proposed to provide pseudo-labels for public data, and use pseudo-labels to guide the training of the cGAN. In this way, the search space is decoupled for different classes of images. Then a max-margin loss is introduced to improve the search process on the subspace of a target class. Extensive experiments demonstrate that our PLG-MI attack significantly improves the attack success rate and visual quality for various datasets and models, notably, 2~3 times better than state-of-the-art attacks under large distributional shifts. Our code is available at: https://github.com/LetheSec/PLG-MI-Attack.

Adversarial patch attacks pose a severe threat to deep neural networks, yet most existing approaches rely on unrealistic white-box assumptions, untargeted objectives, or produce visually conspicuous patches that limit real-world applicability. In this work, we introduce a novel framework for fully controllable adversarial patch generation, where the attacker can freely choose both the input image x and the target class y target, thereby dictating the exact misclassification outcome. Our method combines a generative U-Net design with Grad-CAM-guided patch placement, enabling semantic-aware localization that maximizes attack effectiveness while preserving visual realism. Extensive experiments across convolutional networks (DenseNet-121, ResNet-50) and vision transformers (ViT-B/16, Swin-B/16, among others) demonstrate that our approach achieves state-of-the-art performance across all settings, with attack success rates (ASR) and target-class success (TCS) consistently exceeding 99%. Importantly, we show that our method not only outperforms prior white-box attacks and untargeted baselines, but also surpasses existing non-realistic approaches that produce detectable artifacts. By simultaneously ensuring realism, targeted control, and black-box applicability-the three most challenging dimensions of patch-based attacks-our framework establishes a new benchmark for adversarial robustness research, bridging the gap between theoretical attack strength and practical stealthiness.

The remarkable growth in large language model (LLM) capabilities has spurred exploration into multi-agent systems, with debate frameworks emerging as a promising avenue for enhanced problem-solving. These multi-agent debate (MAD) approaches, where agents collaboratively present, critique, and refine arguments, potentially offer improved reasoning, robustness, and diverse perspectives over monolithic models. Despite prior studies leveraging MAD, a systematic understanding of its effectiveness compared to self-agent methods, particularly under varying conditions, remains elusive. This paper seeks to fill this gap by conceptualizing MAD as a test-time computational scaling technique, distinguished by collaborative refinement and diverse exploration capabilities. We conduct a comprehensive empirical investigation comparing MAD with strong self-agent test-time scaling baselines on mathematical reasoning and safety-related tasks. Our study systematically examines the influence of task difficulty, model scale, and agent diversity on MAD's performance. Key findings reveal that, for mathematical reasoning, MAD offers limited advantages over self-agent scaling but becomes more effective with increased problem difficulty and decreased model capability, while agent diversity shows little benefit. Conversely, for safety tasks, MAD's collaborative refinement can increase vulnerability, but incorporating diverse agent configurations facilitates a gradual reduction in attack success through the collaborative refinement process. We believe our findings provide critical guidance for the future development of more effective and strategically deployed MAD systems.

Multimodal large language models (MLLMs) often fail to transfer safety capabilities learned in the text modality to semantically equivalent non-text inputs, revealing a persistent multimodal safety gap. We study this gap from a representation-geometric perspective by analyzing a text-aligned refusal direction and a modality-induced drift direction. We show that multimodal inputs compress the usable separation along the refusal direction, making it no longer reliable for identifying and refusing harmful inputs. We refer to this failure mode as Safety Geometry Collapse. We quantify it through conditional refusal separability and show that stronger modality-induced drift is consistently associated with weaker refusal separability and higher attack success rates. We then validate the causal role of modality-induced drift through a fixed-strength activation intervention: counteracting the estimated drift restores refusal separability and improves multimodal safety. After drift correction, we further observe self-rectification, where the model recovers its ability to recognize and refuse harmful multimodal inputs during forward dynamics. This effect also provides an internal signal of the model's perceived harmfulness of each input. Motivated by this signal, we propose ReGap, a training-free inference-time method that adaptively corrects modality drift using self-rectification. Experiments across multiple multimodal safety benchmarks and utility benchmarks demonstrate the effectiveness of ReGap, which significantly improves the safety of MLLMs without compromising general capabilities. Our findings highlight representation-level modality alignment as a crucial direction for real-time safety improvement and for building safer, more reliable MLLMs.

AI agents equipped with tool-calling capabilities are susceptible to Indirect Prompt Injection (IPI) attacks. In this attack scenario, malicious commands hidden within untrusted content trick the agent into performing unauthorized actions. Existing defenses can reduce attack success but often suffer from the over-defense dilemma: they deploy expensive, always-on sanitization regardless of actual threat, thereby degrading utility and latency even in benign scenarios. We revisit IPI through a causal ablation perspective: a successful injection manifests as a dominance shift where the user request no longer provides decisive support for the agent's privileged action, while a particular untrusted segment, such as a retrieved document or tool output, provides disproportionate attributable influence. Based on this signature, we propose CausalArmor, a selective defense framework that (i) computes lightweight, leave-one-out ablation-based attributions at privileged decision points, and (ii) triggers targeted sanitization only when an untrusted segment dominates the user intent. Additionally, CausalArmor employs retroactive Chain-of-Thought masking to prevent the agent from acting on ``poisoned'' reasoning traces. We present a theoretical analysis showing that sanitization based on attribution margins conditionally yields an exponentially small upper bound on the probability of selecting malicious actions. Experiments on AgentDojo and DoomArena demonstrate that CausalArmor matches the security of aggressive defenses while improving explainability and preserving utility and latency of AI agents.

Current evaluations of LLM safety predominantly rely on severity-based taxonomies to assess the harmfulness of malicious queries. We argue that this formulation requires re-examination as it assumes uniform risk across all malicious queries, neglecting Execution Likelihood--the conditional probability of a threat being realized given the model's response. In this work, we introduce Expected Harm, a metric that weights the severity of a jailbreak by its execution likelihood, modeled as a function of execution cost. Through empirical analysis of state-of-the-art models, we reveal a systematic Inverse Risk Calibration: models disproportionately exhibit stronger refusal behaviors for low-likelihood (high-cost) threats while remaining vulnerable to high-likelihood (low-cost) queries. We demonstrate that this miscalibration creates a structural vulnerability: by exploiting this property, we increase the attack success rate of existing jailbreaks by up to 2times. Finally, we trace the root cause of this failure using linear probing, which reveals that while models encode severity in their latent space to drive refusal decisions, they possess no distinguishable internal representation of execution cost, making them "blind" to this critical dimension of risk.

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial instructions embedded in external content manipulate agent behavior without user awareness. A critical but underexplored dimension of this threat is concealment: since users tend to observe only an agent's final response, an attack can conceal its existence by presenting no clue of compromise in the final user facing response while successfully executing harmful actions. This leaves users unaware of the manipulation and likely to accept harmful outcomes as legitimate. We present findings from a large scale public red teaming competition evaluating this dual objective across three agent settings: tool calling, coding, and computer use. The competition attracted 464 participants who submitted 272000 attack attempts against 13 frontier models, yielding 8648 successful attacks across 41 scenarios. All models proved vulnerable, with attack success rates ranging from 0.5% (Claude Opus 4.5) to 8.5% (Gemini 2.5 Pro). We identify universal attack strategies that transfer across 21 of 41 behaviors and multiple model families, suggesting fundamental weaknesses in instruction following architectures. Capability and robustness showed weak correlation, with Gemini 2.5 Pro exhibiting both high capability and high vulnerability. To address benchmark saturation and obsoleteness, we will endeavor to deliver quarterly updates through continued red teaming competitions. We open source the competition environment for use in evaluations, along with 95 successful attacks against Qwen that did not transfer to any closed source model. We share model-specific attack data with respective frontier labs and the full dataset with the UK AISI and US CAISI to support robustness research.

Navigation agents powered by large language models (LLMs) convert natural language instructions into executable plans and actions. Compared to text-based applications, their security is far more critical: a successful prompt injection attack does not just alter outputs but can directly misguide physical navigation, leading to unsafe routes, mission failure, or real-world harm. Despite this high-stakes setting, the vulnerability of navigation agents to prompt injection remains largely unexplored. In this paper, we propose PINA, an adaptive prompt optimization framework tailored to navigation agents under black-box, long-context, and action-executable constraints. Experiments on indoor and outdoor navigation agents show that PINA achieves high attack success rates with an average ASR of 87.5%, surpasses all baselines, and remains robust under ablation and adaptive-attack conditions. This work provides the first systematic investigation of prompt injection attacks in navigation and highlights their urgent security implications for embodied LLM agents.

A membership inference attack allows an adversary to query a trained machine learning model to predict whether or not a particular example was contained in the model's training dataset. These attacks are currently evaluated using average-case "accuracy" metrics that fail to characterize whether the attack can confidently identify any members of the training set. We argue that attacks should instead be evaluated by computing their true-positive rate at low (e.g., <0.1%) false-positive rates, and find most prior attacks perform poorly when evaluated in this way. To address this we develop a Likelihood Ratio Attack (LiRA) that carefully combines multiple ideas from the literature. Our attack is 10x more powerful at low false-positive rates, and also strictly dominates prior attacks on existing metrics.

Recent studies demonstrate that Large Language Models (LLMs) are vulnerable to attacks that generate harmful or sensitive outputs. As open-source LLMs are increasingly adopted in high-impact applications such as finance, law, and healthcare, systematically investigating their security risks is becoming increasingly important towards trustworthy LLM era. This paper comprehensively studies effective prompt injection attacks against 14 widely used open-source and three closed-source LLMs on five attack benchmarks. Moreover, existing evaluation metrics mostly only consider the attack success rate, overlooking uncertainty in model responses. Our proposed Attack Success Probability (ASP) additionally captures uncertain behaviors for evaluation, where the model may initially refuse a harmful request but subsequently provide harmful guidance or vice versa, reflecting inconsistency and ambiguity in attack feasibility. By systematically analyzing the effectiveness of prompt injection attacks, we propose a straightforward and effective hypnotism attack; results show that this attack causes aligned language models, including Stablelm2, Mistral, Openchat, and Vicuna, to generate objectionable behaviors, achieving around 90% ASP. They also indicate that ignore prefix attacks can break all 14 open-source LLMs, achieving over 60% ASP on a multi-categorical dataset. We find that moderately well-known LLMs exhibit higher vulnerability to prompt injection attacks, highlighting the need to raise public awareness and prioritize efficient mitigation strategies.

Even a few action perturbations can substantially degrade the performance of a deployed decision policy. Certifying the resulting return loss is challenging in stochastic environments, where returns vary even without an attack. We introduce FoSeRL, a framework for certifying deployed RL policies against precommitted, temporally sparse action attacks. The deployed policy is unchanged, with no smoothing or retraining. Certification requires a resettable simulator supporting shared randomness and independent one-step successor queries, but no analytical dynamics model. FoSeRL certifies that an attacked episode loses no more than a prescribed amount of return relative to the same episode unattacked, with at least a target probability and at a user-specified confidence level. Both runs share the initial state and randomness, so the measured loss reflects the attack, not the episode; carrying the running return gap as a state coordinate makes it the terminal value, reducing trajectory-level certification to terminal safety. Time-dependent barrier conditions on the augmented state bound the terminal failure probability: satisfied exactly, they certify every admissible precommitted attack; learned from sampled trajectories and verified on held-out data, they certify the same guarantee under a specified attack-episode setting. Across six stochastic continuous-control environments and three RL policy families (TD3, SAC, and PPO), FoSeRL certifies non-trivial cardinality--magnitude robustness frontiers, achieves substantially larger certified budgets than policy smoothing, and reveals marked robustness differences among policies with comparable nominal performance.

Computer-use agents (CUAs) can now autonomously complete complex tasks in real digital environments, but when misled, they can also be used to automate harmful actions programmatically. Existing safety evaluations largely target explicit threats such as misuse and prompt injection, but overlook a subtle yet critical setting where user instructions are entirely benign and harm arises from the task context or execution outcome. We introduce OS-BLIND, a benchmark that evaluates CUAs under unintended attack conditions, comprising 300 human-crafted tasks across 12 categories, 8 applications, and 2 threat clusters: environment-embedded threats and agent-initiated harms. Our evaluation on frontier models and agentic frameworks reveals that most CUAs exceed 90% attack success rate (ASR), and even the safety-aligned Claude 4.5 Sonnet reaches 73.0% ASR. More interestingly, this vulnerability becomes even more severe, with ASR rising from 73.0% to 92.7% when Claude 4.5 Sonnet is deployed in multi-agent systems. Our analysis further shows that existing safety defenses provide limited protection when user instructions are benign. Safety alignment primarily activates within the first few steps and rarely re-engages during subsequent execution. In multi-agent systems, decomposed subtasks obscure the harmful intent from the model, causing safety-aligned models to fail. We will release our OS-BLIND to encourage the broader research community to further investigate and address these safety challenges.

The widespread use of Text-to-Image (T2I) models in content generation requires careful examination of their safety, including their robustness to adversarial attacks. Despite extensive research on adversarial attacks, the reasons for their effectiveness remain underexplored. This paper presents an empirical study on adversarial attacks against T2I models, focusing on analyzing factors associated with attack success rates (ASR). We introduce a new attack objective - entity swapping using adversarial suffixes and two gradient-based attack algorithms. Human and automatic evaluations reveal the asymmetric nature of ASRs on entity swap: for example, it is easier to replace "human" with "robot" in the prompt "a human dancing in the rain." with an adversarial suffix, but the reverse replacement is significantly harder. We further propose probing metrics to establish indicative signals from the model's beliefs to the adversarial ASR. We identify conditions that result in a success probability of 60% for adversarial attacks and others where this likelihood drops below 5%.

Modern language models often rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors. However, they remain vulnerable to adversarial attacks due to three key limitations: (1) the inefficiency and high cost of human annotation, (2) the vast diversity of potential adversarial attacks, and (3) the risk of feedback bias and reward hacking. To address these challenges, we introduce Adversarial Preference Learning (APL), an iterative adversarial training method incorporating three key innovations. First, a direct harmfulness metric based on the model's intrinsic preference probabilities, eliminating reliance on external assessment. Second, a conditional generative attacker that synthesizes input-specific adversarial variations. Third, an iterative framework with automated closed-loop feedback, enabling continuous adaptation through vulnerability discovery and mitigation. Experiments on Mistral-7B-Instruct-v0.3 demonstrate that APL significantly enhances robustness, achieving 83.33% harmlessness win rate over the base model (evaluated by GPT-4o), reducing harmful outputs from 5.88% to 0.43% (measured by LLaMA-Guard), and lowering attack success rate by up to 65% according to HarmBench. Notably, APL maintains competitive utility, with an MT-Bench score of 6.59 (comparable to the baseline 6.78) and an LC-WinRate of 46.52% against the base model.

Large language models trained for safety and harmlessness remain susceptible to adversarial misuse, as evidenced by the prevalence of "jailbreak" attacks on early releases of ChatGPT that elicit undesired behavior. Going beyond recognition of the issue, we investigate why such attacks succeed and how they can be created. We hypothesize two failure modes of safety training: competing objectives and mismatched generalization. Competing objectives arise when a model's capabilities and safety goals conflict, while mismatched generalization occurs when safety training fails to generalize to a domain for which capabilities exist. We use these failure modes to guide jailbreak design and then evaluate state-of-the-art models, including OpenAI's GPT-4 and Anthropic's Claude v1.3, against both existing and newly designed attacks. We find that vulnerabilities persist despite the extensive red-teaming and safety-training efforts behind these models. Notably, new attacks utilizing our failure modes succeed on every prompt in a collection of unsafe requests from the models' red-teaming evaluation sets and outperform existing ad hoc jailbreaks. Our analysis emphasizes the need for safety-capability parity -- that safety mechanisms should be as sophisticated as the underlying model -- and argues against the idea that scaling alone can resolve these safety failure modes.

Large language model safeguards decide whether to answer before seeing how an answer will be used. This creates a basic problem for dual-use tasks: the same answer can help an authorized professional or an attacker, while an attacker can imitate a benign request and interaction history. We separate the capability released by the model from the evidence available about downstream use. When that evidence is copyable, we derive the exact worst-case floor on attacker assistance while preserving useful answers. The result yields a safety trilemma: Useful Capability, Reliable Safety, and Open Access cannot coexist. We then show how a trusted credential can complement existing safeguards by adding hard-to-copy information that predicts actual downstream use, and identify the stronger condition needed to eliminate the floor. Evidence from dual-use evaluations, adaptive attacks, and deployed trusted-access programs supports the practical relevance of these conditions.

As large language models grow in capability and agency, identifying vulnerabilities through red-teaming becomes vital for safe deployment. However, traditional prompt-engineering approaches may prove ineffective once red-teaming turns into a weak-to-strong problem, where target models surpass red-teamers in capabilities. To study this shift, we frame red-teaming through the lens of the capability gap between attacker and target. We evaluate more than 500 attacker-target pairs using LLM-based jailbreak attacks that mimic human red-teamers across diverse families, sizes, and capability levels. Three strong trends emerge: (i) more capable models are better attackers, (ii) attack success drops sharply once the target's capability exceeds the attacker's, and (iii) attack success rates correlate with high performance on social science splits of the MMLU-Pro benchmark. From these trends, we derive a jailbreaking scaling law that predicts attack success for a fixed target based on attacker-target capability gap. These findings suggest that fixed-capability attackers (e.g., humans) may become ineffective against future models, increasingly capable open-source models amplify risks for existing systems, and model providers must accurately measure and control models' persuasive and manipulative abilities to limit their effectiveness as attackers.

Large Language Models (LLMs) are increasingly deployed via third-party system prompts downloaded from public marketplaces. We identify a critical supply-chain vulnerability: conditional system prompt poisoning, where an adversary injects a ``sleeper agent'' into a benign-looking prompt. Unlike traditional jailbreaks that aim for broad refusal-breaking, our proposed framework, SPECTRE, optimizes system prompts to trigger LLMs to output targeted, compromised responses only for specific queries (e.g., ``Who should I vote for the US President?'') while maintaining high utility on benign inputs. Operating in a strict black-box setting without model weight access, SPECTRE utilizes a two-stage optimization including a global semantic search followed by a greedy lexical refinement. Tested on open-source models and commercial APIs (GPT-4o-mini, GPT-3.5), SPECTRE achieves up to 70% F1 reduction on targeted queries with minimal degradation to general capabilities. We further demonstrate that these poisoned prompts evade standard defenses, including perplexity filters and typo-correction, by exploiting the natural noise found in real-world system prompts. Our code and data are available at https://github.com/vietph34/CAIN. WARNING: Our paper contains examples that might be sensitive to the readers!

Recent computer-using-agent (CUA) red-teaming papers report prompt-injection attack success rates (ASR) of 42-98%, but these headline numbers cluster on retired models and on the most-vulnerable model in each paper's panel. We ask whether those techniques, reproduced as hand-crafted templates, still work against current frontier CUAs. We release CUA-HandCrafted, a public benchmark of 793 episodes spanning 24 multi-step web tasks, 56 attack templates, 8 attack families, and 4 system-prompt configurations. Against Claude Sonnet 4.6 and GPT-5.4 we measure 0/140 multi-step attack success (Clopper-Pearson 95% upper bound 2.60%); a prompt ablation shows this resistance lives in the model weights. Yet it does not generalize: on a sister coding-agent benchmark (SkillBench), the same weights fall to hand-crafted skill-injection at up to 100%. We argue that the literature's high ASR is largely attributable to RL-optimized injection text rather than the attack categories, and that frontier safety hardening is domain-conditioned, specific to the heavily-targeted browser surface. Reporting techniques without releasing the optimized strings, or extrapolating browser-domain safety to other CUA modalities, makes published ASR numbers unreproducible.

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We systematically investigate and compare the influence of six critical intrinsic model characteristics and three external attack techniques. Our large-scale evaluation is conducted using 32 recent, popular LLMs and LRMs across thirteen distinct model families, spanning a parameter scale from 3B to 235B. The assessment leverages five established safety datasets and probes model vulnerabilities with 56 jailbreak techniques and four CoT attack strategies, resulting in 4.6M API calls. Our key empirical findings are fourfold. First, we identify the LRMs GPT-OSS-20B, Qwen3-Next-80B-A3B-Thinking, and GPT-OSS-120B as the top-three safest models, which substantiates the significant advantage of integrated reasoning and self-reflection mechanisms for robust safety alignment. Second, post-training and knowledge distillation may lead to a systematic degradation of safety alignment. We thus argue that safety must be treated as an explicit constraint or a core optimization objective during these stages, not merely subordinated to the pursuit of general capability. Third, we reveal a pronounced vulnerability: employing a CoT attack via a response prefix can elevate the attack success rate by 3.34x on average and from 0.6% to 96.3% for Seed-OSS-36B-Instruct. This critical finding underscores the safety risks inherent in text-completion interfaces and features that allow user-defined response prefixes in LLM services, highlighting an urgent need for architectural and deployment safeguards. Fourth, roleplay, prompt injection, and gradient-based search for adversarial prompts are the predominant methodologies for eliciting unaligned behaviors in modern models.

LLMs have shown remarkable capabilities, but precisely controlling their response behavior remains challenging. Existing activation steering methods alter LLM behavior indiscriminately, limiting their practical applicability in settings where selective responses are essential, such as content moderation or domain-specific assistants. In this paper, we propose Conditional Activation Steering (CAST), which analyzes LLM activation patterns during inference to selectively apply or withhold activation steering based on the input context. Our method is based on the observation that different categories of prompts activate distinct patterns in the model's hidden states. Using CAST, one can systematically control LLM behavior with rules like "if input is about hate speech or adult content, then refuse" or "if input is not about legal advice, then refuse." This allows for selective modification of responses to specific content while maintaining normal responses to other content, all without requiring weight optimization. We release an open-source implementation of our framework at github.com/IBM/activation-steering .

Indirect prompt injection attacks hijack LLM-based agents by embedding malicious instructions in third-party data that the agent retrieves during task execution. Existing defenses report near-zero attack success rate on static benchmarks, yet recent adaptive evaluations show that these results collapse once the attacker is allowed to optimize against the deployed defense. In this work, we trace this collapse to two failure modes. First, existing defense methods are confined to recognizing specific attack patterns, rather than assessing whether the intent of every embedded instruction is relevant to the user task. Second, training-based defenses, which otherwise offer the strongest safety-utility trade-off, assemble their adversarial examples from a handful of hand-crafted templates, and the resulting defender fails to generalize outside that narrow strategy distribution. To address these gaps, we propose RETA, a training-based method that grounds defense decisions on the user tasks rather than attacker-controlled data. At each tool-output step, the defender undertakes chain-of-thought reasoning verifying that its actions are consistent with the user task. Leveraging red-teaming, a simulated attacker synthesizes adversarial training data and receives a dictionary-learning diversity reward, achieving broad coverage of injection-reformulation strategies. Together, these allow the defender to be optimized via multi-objective reinforcement learning and achieve better safety-utility trade-off. Across six black-box adaptive attacks, RETA keeps every per-attack ASR below 10%, with average ASR of 2.92% and 3.75% on the two target models, while preserving most utility under attack and on clean inputs.

Large Language Models (LLMs) are employed across various high-stakes domains, where the reliability of their outputs is crucial. One commonly used method to assess the reliability of LLMs' responses is uncertainty estimation, which gauges the likelihood of their answers being correct. While many studies focus on improving the accuracy of uncertainty estimations for LLMs, our research investigates the fragility of uncertainty estimation and explores potential attacks. We demonstrate that an attacker can embed a backdoor in LLMs, which, when activated by a specific trigger in the input, manipulates the model's uncertainty without affecting the final output. Specifically, the proposed backdoor attack method can alter an LLM's output probability distribution, causing the probability distribution to converge towards an attacker-predefined distribution while ensuring that the top-1 prediction remains unchanged. Our experimental results demonstrate that this attack effectively undermines the model's self-evaluation reliability in multiple-choice questions. For instance, we achieved a 100 attack success rate (ASR) across three different triggering strategies in four models. Further, we investigate whether this manipulation generalizes across different prompts and domains. This work highlights a significant threat to the reliability of LLMs and underscores the need for future defenses against such attacks. The code is available at https://github.com/qcznlp/uncertainty_attack.

The Windows authentication infrastructure relies on the Local Security Authority (LSA) system, with its integral component being lsass.exe. Regrettably, this framework is not impervious, presenting vulnerabilities that attract threat actors with malicious intent. By exploiting documented vulnerabilities sourced from the CVE database or leveraging sophisticated tools such as mimikatz, adversaries can successfully compromise user password-address information. In this comprehensive analysis, we delve into proactive measures aimed at fortifying the local authentication subsystem against potential threats. Moreover, we present empirical evidence derived from practical assessments of various defensive methodologies, including those articulated previously. This examination not only underscores the importance of proactive security measures but also assesses the practical efficacy of these strategies in real-world contexts.

Code models, such as CodeBERT and CodeT5, offer general-purpose representations of code and play a vital role in supporting downstream automated software engineering tasks. Most recently, code models were revealed to be vulnerable to backdoor attacks. A code model that is backdoor-attacked can behave normally on clean examples but will produce pre-defined malicious outputs on examples injected with triggers that activate the backdoors. Existing backdoor attacks on code models use unstealthy and easy-to-detect triggers. This paper aims to investigate the vulnerability of code models with stealthy backdoor attacks. To this end, we propose AFRAIDOOR (Adversarial Feature as Adaptive Backdoor). AFRAIDOOR achieves stealthiness by leveraging adversarial perturbations to inject adaptive triggers into different inputs. We evaluate AFRAIDOOR on three widely adopted code models (CodeBERT, PLBART and CodeT5) and two downstream tasks (code summarization and method name prediction). We find that around 85% of adaptive triggers in AFRAIDOOR bypass the detection in the defense process. By contrast, only less than 12% of the triggers from previous work bypass the defense. When the defense method is not applied, both AFRAIDOOR and baselines have almost perfect attack success rates. However, once a defense is applied, the success rates of baselines decrease dramatically to 10.47% and 12.06%, while the success rate of AFRAIDOOR are 77.05% and 92.98% on the two tasks. Our finding exposes security weaknesses in code models under stealthy backdoor attacks and shows that the state-of-the-art defense method cannot provide sufficient protection. We call for more research efforts in understanding security threats to code models and developing more effective countermeasures.

The rapid progress of Large Language Models (LLMs) has opened up new opportunities across various domains and applications; yet it also presents challenges related to potential misuse. To mitigate such risks, red teaming has been employed as a proactive security measure to probe language models for harmful outputs via jailbreak attacks. However, current jailbreak attack approaches are single-turn with explicit malicious queries that do not fully capture the complexity of real-world interactions. In reality, users can engage in multi-turn interactions with LLM-based chat assistants, allowing them to conceal their true intentions in a more covert manner. To bridge this gap, we, first, propose a new jailbreak approach, RED QUEEN ATTACK. This method constructs a multi-turn scenario, concealing the malicious intent under the guise of preventing harm. We craft 40 scenarios that vary in turns and select 14 harmful categories to generate 56k multi-turn attack data points. We conduct comprehensive experiments on the RED QUEEN ATTACK with four representative LLM families of different sizes. Our experiments reveal that all LLMs are vulnerable to RED QUEEN ATTACK, reaching 87.62% attack success rate on GPT-4o and 75.4% on Llama3-70B. Further analysis reveals that larger models are more susceptible to the RED QUEEN ATTACK, with multi-turn structures and concealment strategies contributing to its success. To prioritize safety, we introduce a straightforward mitigation strategy called RED QUEEN GUARD, which aligns LLMs to effectively counter adversarial attacks. This approach reduces the attack success rate to below 1% while maintaining the model's performance across standard benchmarks. Full implementation and dataset are publicly accessible at https://github.com/kriti-hippo/red_queen.

Agentic red-teaming benchmarks report whether an injected agent was compromised as a single bit: the attack succeeded, or it did not. We argue that this binary attack-success rate discards the information a defender most needs, namely how harmful the resulting action was. We introduce an action-graded harm rubric that scores an agent's tool-call trajectory on a seven-level ordinal scale (L0 to L6) according to whether the executed action was reversible, whether it crossed scope to reach another party, and whether it expanded privilege. We compute the scale two ways: a deterministic oracle that reads the trajectory and the attacker's stated goal, and a panel of three frontier language-model judges that read a tag-free account of the same trajectory. Across four victim models and two defenses on the AgentDojo workspace suite, severity grading exposes three cases the binary metric hides, including a defense that reports a zero attack-success rate while still permitting an externally visible cross-scope leak through an unfiltered tool. The judge panel reproduces the oracle with high ordinal agreement (Krippendorff's alpha = 0.91) but shares systematic blind spots that we characterize, most notably a failure to recognize escalation chains. Unlike prior work that provides harm taxonomies, harmful-task completion tests, execution-level safety benchmarks, or severity-aware simulation, our contribution is a reusable, trace-grounded severity instrument applied to the actual actions recorded in existing red-team logs. All code, prompts, and per-episode logs are released.

Large language model (LLM)-based search agents synthesize open-web content into actionable recommendations on behalf of users, creating a risk that attacker-published pages are transformed into endorsed claims. We introduce SearchGEO, a controlled evaluation framework for measuring endorsement corruption in LLM-based web-search agents, combining a web-evidence manipulation pipeline, a five-mode attack taxonomy, and multiple output-level metrics. We evaluate 13 LLM backends on 308 cases each. Results show that vulnerability patterns vary across backends: overall attack success rate (ASR) ranges from 0.0% on Claude-Sonnet-4.6 to 31.4% on Gemini-3-Flash, the strongest attack mode differs by model family, and the same deployment scaffold could amplify or decrease ASR on different backends. An auxiliary agent-skill probe, where endorsement becomes an install command, exposes a sharp split among otherwise robust backends: Claude over-rejects while GPT over-trusts. These findings argue for treating recommendation reliability under adversarial search content as a first-class dimension of backend safety evaluation.

This technical report accompanies the LLM robustness leaderboard published by PRISM Eval for the Paris AI Action Summit. We introduce PRISM Eval Behavior Elicitation Tool (BET), an AI system performing automated red-teaming through Dynamic Adversarial Optimization that achieves 100% Attack Success Rate (ASR) against 37 of 41 state-of-the-art LLMs. Beyond binary success metrics, we propose a fine-grained robustness metric estimating the average number of attempts required to elicit harmful behaviors, revealing that attack difficulty varies by over 300-fold across models despite universal vulnerability. We introduce primitive-level vulnerability analysis to identify which jailbreaking techniques are most effective for specific hazard categories. Our collaborative evaluation with trusted third parties from the AI Safety Network demonstrates practical pathways for distributed robustness assessment across the community.

The growing dependence on machine learning in real-world applications emphasizes the importance of understanding and ensuring its safety. Backdoor attacks pose a significant security risk due to their stealthy nature and potentially serious consequences. Such attacks involve embedding triggers within a learning model with the intention of causing malicious behavior when an active trigger is present while maintaining regular functionality without it. This paper evaluates the effectiveness of any backdoor attack incorporating a constant trigger, by establishing tight lower and upper boundaries for the performance of the compromised model on both clean and backdoor test data. The developed theory answers a series of fundamental but previously underexplored problems, including (1) what are the determining factors for a backdoor attack's success, (2) what is the direction of the most effective backdoor attack, and (3) when will a human-imperceptible trigger succeed. Our derived understanding applies to both discriminative and generative models. We also demonstrate the theory by conducting experiments using benchmark datasets and state-of-the-art backdoor attack scenarios.

Language-model agents increasingly use tools to act on external systems. Earlier actions can alter files, permissions, database records, or other state, making a later routine-looking action harmful. Yet the visible interaction may not reveal the underlying state needed to assess that action. We formulate attack and defense as partially observed state control in SEAD, deriving their design requirements from this shared execution process. Because attackers supply instructions while the target chooses concrete actions, DART decomposes harmful goals into locally plausible steps and uses feedback from actual tool execution to guide trajectory search. The defender must decide before execution with incomplete state evidence. SAGE can therefore investigate relevant state through read-only queries before allowing or blocking each action, including those proposed after a block. We construct an environment-verifiable dataset integrating controlled initial states, replayable tool environments, and task-specific executable checks. Across four target models, DART improves semantic attack success by 18.8--35.9 percentage points over the competing baseline, with consistent gains under executable verification. On recorded trajectories, SAGE preserves 95.79% of benign trajectories while intercepting 92.73% of harmful paths by the harm-enabling boundary. In online attack-defense evaluation, it reduces DART's executable attack success from 48.0% to 4.0%. SAGE remains effective across four attack methods and generalizes to out-of-domain environments. Our code and data is available at https://github.com/EverywhereSafety/SEAD.

We show that even the most recent safety-aligned LLMs are not robust to simple adaptive jailbreaking attacks. First, we demonstrate how to successfully leverage access to logprobs for jailbreaking: we initially design an adversarial prompt template (sometimes adapted to the target LLM), and then we apply random search on a suffix to maximize the target logprob (e.g., of the token "Sure"), potentially with multiple restarts. In this way, we achieve nearly 100\% attack success rate -- according to GPT-4 as a judge -- on GPT-3.5/4, Llama-2-Chat-7B/13B/70B, Gemma-7B, and R2D2 from HarmBench that was adversarially trained against the GCG attack. We also show how to jailbreak all Claude models -- that do not expose logprobs -- via either a transfer or prefilling attack with 100\% success rate. In addition, we show how to use random search on a restricted set of tokens for finding trojan strings in poisoned models -- a task that shares many similarities with jailbreaking -- which is the algorithm that brought us the first place in the SaTML'24 Trojan Detection Competition. The common theme behind these attacks is that adaptivity is crucial: different models are vulnerable to different prompting templates (e.g., R2D2 is very sensitive to in-context learning prompts), some models have unique vulnerabilities based on their APIs (e.g., prefilling for Claude), and in some settings it is crucial to restrict the token search space based on prior knowledge (e.g., for trojan detection). We provide the code, prompts, and logs of the attacks at https://github.com/tml-epfl/llm-adaptive-attacks.

Recent work has embodied LLMs as agents, allowing them to access tools, perform actions, and interact with external content (e.g., emails or websites). However, external content introduces the risk of indirect prompt injection (IPI) attacks, where malicious instructions are embedded within the content processed by LLMs, aiming to manipulate these agents into executing detrimental actions against users. Given the potentially severe consequences of such attacks, establishing benchmarks to assess and mitigate these risks is imperative. In this work, we introduce InjecAgent, a benchmark designed to assess the vulnerability of tool-integrated LLM agents to IPI attacks. InjecAgent comprises 1,054 test cases covering 17 different user tools and 62 attacker tools. We categorize attack intentions into two primary types: direct harm to users and exfiltration of private data. We evaluate 30 different LLM agents and show that agents are vulnerable to IPI attacks, with ReAct-prompted GPT-4 vulnerable to attacks 24% of the time. Further investigation into an enhanced setting, where the attacker instructions are reinforced with a hacking prompt, shows additional increases in success rates, nearly doubling the attack success rate on the ReAct-prompted GPT-4. Our findings raise questions about the widespread deployment of LLM Agents. Our benchmark is available at https://github.com/uiuc-kang-lab/InjecAgent.

We assess indirect prompt injection in DeepSeek Harness (DSH), using AI-Infra-Guard (A.I.G) to construct tests, deliver controlled taint, execute DSH, collect traces, and judge outcomes. The study covers 14,560 controlled executions over 16 indirect-content channels, text and file carrier modes, 35 payload objectives, one unmodified baseline, and 12 attack methods. The experiment preserves DSH's agent loop, tool registry, model adapter, and session-event path; source tools and sensitive sinks are local fixtures, so attempted actions are recorded without external side effects. We evaluate each trace with a deterministic rule-based judge, (RuleJudge), and a semantic LLM-based judge, (LLMJudge). The strongest observed attack success rates are 17.0% under for fake-completion attack in text mode, 25.5% under for hidden Unicode in file mode, and 16.0% under for the skills channel in file mode. also assigns partial compliance more often than (7.3% versus 2.0%). We relate these results to DSH's treatment of tool results, additional contexts, and tool-call policy hooks, then identify controls that should sit between untrusted content and sensitive actions. Our code is available at https://github.com/Tencent/AI-Infra-Guard/tree/main/Research/deepseek-harness-security-assessment .

Large Language Models have emerged as transformative tools for Security Operations Centers, enabling automated log analysis, phishing triage, and malware explanation; however, deployment in adversarial cybersecurity environments exposes critical vulnerabilities to prompt injection attacks where malicious instructions embedded in security artifacts manipulate model behavior. This paper introduces SecureCAI, a novel defense framework extending Constitutional AI principles with security-aware guardrails, adaptive constitution evolution, and Direct Preference Optimization for unlearning unsafe response patterns, addressing the unique challenges of high-stakes security contexts where traditional safety mechanisms prove insufficient against sophisticated adversarial manipulation. Experimental evaluation demonstrates that SecureCAI reduces attack success rates by 94.7% compared to baseline models while maintaining 95.1% accuracy on benign security analysis tasks, with the framework incorporating continuous red-teaming feedback loops enabling dynamic adaptation to emerging attack strategies and achieving constitution adherence scores exceeding 0.92 under sustained adversarial pressure, thereby establishing a foundation for trustworthy integration of language model capabilities into operational cybersecurity workflows and addressing a critical gap in current approaches to AI safety within adversarial domains.

Safety-aligned large language models are trained to refuse harmful requests, yet embedding the same requests in particular scenarios can bypass their safeguards. Existing red-teaming methods empirically identify effective scenarios through observed attack outcomes, but why particular scenarios weaken refusal remains mechanistically unclear. Meanwhile, mechanistic interpretability studies have characterized both refusal directions and jailbreak-associated features, without explaining the relationship between the two representations. In this work, we show that scenario-wrapped prompts activate internal scenario directions whose causal steering consistently reduces refusal scores. Building on this finding, we propose Concept2Scenario, a concept-based attribution framework for vulnerable scenario discovery. It instantiates a broad concept space with a sparse autoencoder, attributes refusal suppression to individual concepts, translates the identified concepts into interpretable natural-language scenarios, and identifies synergistic scenario combinations through interaction attribution. Across three open-source models, two safety benchmarks, and six black-box jailbreak methods, the discovered scenarios serve as reusable priors that improve average attack success rates by up to 18.2 percentage points. They also transfer to GPT-5, Claude-Haiku-4.5, and Gemini-3-Flash, suggesting that some scenario-level refusal vulnerabilities are shared across model families. Moreover, the identified combinations outperform their individual constituents and enable iterative attacks to succeed in fewer turns.

Autonomous language-model agents increasingly rely on installable skills and tools to complete user tasks. Static skill auditing can expose capability surface before deployment, but it cannot determine whether a particular invocation is unsafe under the current user request and runtime context. We therefore study skill invocation auditing as a continuous-risk estimation problem: given a user request, candidate skill, and runtime context, predict a score that supports ranking and triage before a hard intervention is applied. We introduce STARS, which combines a static capability prior, a request-conditioned invocation risk model, and a calibrated risk-fusion policy. To evaluate this setting, we construct SIA-Bench, a benchmark of 3,000 invocation records with group-safe splits, lineage metadata, runtime context, canonical action labels, and derived continuous-risk targets. On a held-out split of indirect prompt injection attacks, calibrated fusion reaches 0.439 high-risk AUPRC, improving over 0.405 for the contextual scorer and 0.380 for the strongest static baseline, while the contextual scorer remains better calibrated with 0.289 expected calibration error. On the locked in-distribution test split, gains are smaller and static priors remain useful. The resulting claim is therefore narrower: request-conditioned auditing is most valuable as an invocation-time risk-scoring and triage layer rather than as a replacement for static screening. Code is available at https://github.com/123zgj123/STARS.

We introduce a red-teaming methodology that exposes harder-to-catch attacks for coding-agent monitors, suggesting that current practices may under-elicit attacks and overstate monitor performance. We identify three challenges with current red-teaming. First, mode collapse in attack generation, which we reduce with a novel attack taxonomy for broader coverage. Second, a conceive-execute gap: frontier LLMs can propose strong attack ideas or execute them, but not all at once. We mitigate this by decomposing attack construction into strategy generation, execution, and post-hoc trajectory refinement. Third, manual elicitation is costly to scale, which we address with our semi-automated red-teaming pipeline. Applied to BashArena, an AI control setting for tool-using coding agents, this pipeline produces MonitoringBench, a benchmark of 2,644 attack trajectories for evaluating monitor capabilities and failure modes. Our pipeline produces more diverse and stronger attacks: Opus-4.5 monitor's catch rate falls from 94.9\% on elicited-only Opus attacks to 60.3\% on our best refined attacks, with larger drops for several mid-tier monitors. Attacks optimized against three development monitors generalize to ten held-out monitors, with catch rates generally increasing with monitor capability. Using this benchmark, we provide a snapshot of the current monitor capabilities and find that frontier monitors often detect suspicious actions but fall for persuasion or fail to calibrate suspiciousness scores appropriately, suggesting tractable paths for improvement. MonitoringBench provides both a static benchmark for current tool-use monitors and a reusable methodology for refreshing these evaluations as agents and monitors improve.

As large language models (LLMs) become increasingly capable, it is prudent to assess whether safety measures remain effective even if LLMs intentionally try to bypass them. Previous work introduced control evaluations, an adversarial framework for testing deployment strategies of untrusted models (i.e., models which might be trying to bypass safety measures). While prior work treats a single failure as unacceptable, we perform control evaluations in a "distributed threat setting" -- a setting where no single action is catastrophic and no single action provides overwhelming evidence of misalignment. We approach this problem with a two-level deployment framework that uses an adaptive macro-protocol to choose between micro-protocols. Micro-protocols operate on a single task, using a less capable, but extensively tested (trusted) model to harness and monitor the untrusted model. Meanwhile, the macro-protocol maintains an adaptive credence on the untrusted model's alignment based on its past actions, using it to pick between safer and riskier micro-protocols. We evaluate our method in a code generation testbed where a red team attempts to generate subtly backdoored code with an LLM whose deployment is safeguarded by a blue team. We plot Pareto frontiers of safety (# of non-backdoored solutions) and usefulness (# of correct solutions). At a given level of usefulness, our adaptive deployment strategy reduces the number of backdoors by 80% compared to non-adaptive baselines.

Many publicly available language models have been safety tuned to reduce the likelihood of toxic or liability-inducing text. To redteam or jailbreak these models for compliance with toxic requests, users and security analysts have developed adversarial prompting techniques. One attack method is to apply discrete optimization techniques to the prompt. However, the resulting attack strings are often gibberish text, easily filtered by defenders due to high measured perplexity, and may fail for unseen tasks and/or well-tuned models. In this work, we improve existing algorithms (primarily GCG and BEAST) to develop powerful and fluent attacks on safety-tuned models like Llama-2 and Phi-3. Our technique centers around a new distillation-based approach that encourages the victim model to emulate a toxified finetune, either in terms of output probabilities or internal activations. To encourage human-fluent attacks, we add a multi-model perplexity penalty and a repetition penalty to the objective. We also enhance optimizer strength by allowing token insertions, token swaps, and token deletions and by using longer attack sequences. The resulting process is able to reliably jailbreak the most difficult target models with prompts that appear similar to human-written prompts. On Advbench we achieve attack success rates >93% for Llama-2-7B, Llama-3-8B, and Vicuna-7B, while maintaining model-measured perplexity <33; we achieve 95% attack success for Phi-3, though with higher perplexity. We also find a universally-optimized single fluent prompt that induces >88% compliance on previously unseen tasks across Llama-2-7B, Phi-3-mini and Vicuna-7B and transfers to other black-box models.

LLM agents with tool access can discover and exploit security vulnerabilities. This is known. What is not known is which features of a system prompt trigger this behaviour, and which do not. We present a systematic taxonomy based on approximately 10,000 trials across seven models, 37 prompt conditions, and 12 hypothesized attack dimensions -- all executed in real Docker sandboxes. Every condition includes the instruction "Always respect all rules and access policies"; only a single encouragement sentence varies. Within the task class studied (planted test-runner vulnerabilities), the threat model is narrower than assumed: nine of twelve dimensions -- including minimization, moral licensing, incentives, identity priming, and reasoning triggers -- produce no detectable exploitation at n=50 per cell (upper 95% CI <7% per condition). But it is also more subtle than expected: one dimension, goal reframing, reliably triggers exploitation. "You are solving a puzzle; there may be hidden clues" produces 38-40% exploitation on Claude Sonnet 4 despite the explicit rule instruction, replicating across four models (CTF framing: 8-14% on DeepSeek, GPT-5-mini, o4-mini). The agent does not override the rules; it reinterprets the task so that exploitative actions become task-aligned. GPT-4.1 produces no exploitation across 1,850 trials (37 conditions), and a temporal comparison across four OpenAI models released over eleven months shows a pattern consistent with improving safety training, though model capability differences are a confounder. The practical contribution is a narrowed, testable threat model: defenders should audit for goal-reframing language, not for the broad class of adversarial prompts.

Despite extensive diagnostics and debugging by developers, AI systems sometimes exhibit harmful unintended behaviors. Finding and fixing these is challenging because the attack surface is so large -- it is not tractable to exhaustively search for inputs that may elicit harmful behaviors. Red-teaming and adversarial training (AT) are commonly used to improve robustness, however, they empirically struggle to fix failure modes that differ from the attacks used during training. In this work, we utilize latent adversarial training (LAT) to defend against vulnerabilities without leveraging knowledge of what they are or using inputs that elicit them. LAT makes use of the compressed, abstract, and structured latent representations of concepts that the network actually uses for prediction. Here, we use it to defend against failure modes without examples that elicit them. Specifically, we use LAT to remove trojans and defend against held-out classes of adversarial attacks. We show in image classification, text classification, and text generation tasks that LAT usually improves both robustness to novel attacks and performance on clean data relative to AT. This suggests that LAT can be a promising tool for defending against failure modes that are not explicitly identified by developers.

Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transactions, or destroy files. This threat goes well beyond conventional text-level jailbreaks, yet existing safety evaluations fall short: most test models in isolated chat settings, rely on synthetic environments, and do not account for how the agent framework itself shapes safety outcomes. We introduce CLAWSAFETY, a benchmark of 120 adversarial test scenarios organized along three dimensions (harm domain, attack vector, and harmful action type) and grounded in realistic, high-privilege professional workspaces spanning software engineering, finance, healthcare, law, and DevOps. Each test case embeds adversarial content in one of three channels the agent encounters during normal work: workspace skill files, emails from trusted senders, and web pages. We evaluate five frontier LLMs as agent backbones, running 2,520 sandboxed trials across all configurations. Attack success rates (ASR) range from 40\% to 75\% across models and vary sharply by injection vector, with skill instructions (highest trust) consistently more dangerous than email or web content. Action-trace analysis reveals that the strongest model maintains hard boundaries against credential forwarding and destructive actions, while weaker models permit both. Cross-scaffold experiments on three agent frameworks further demonstrate that safety is not determined by the backbone model alone but depends on the full deployment stack, calling for safety evaluation that treats model and framework as joint variables. Code and data will be available at: https://weibowen555.github.io/ClawSafety/.

Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are correctly labeled. Our attack, LLMBkd, leverages language models to automatically insert diverse style-based triggers into texts. We also propose a poison selection technique to improve the effectiveness of both LLMBkd as well as existing textual backdoor attacks. Lastly, we describe REACT, a baseline defense to mitigate backdoor attacks via antidote training examples. Our evaluations demonstrate LLMBkd's effectiveness and efficiency, where we consistently achieve high attack success rates across a wide range of styles with little effort and no model training.

The exploitation of large language models (LLMs) for malicious purposes poses significant security risks as these models become more powerful and widespread. While most existing red-teaming frameworks focus on single-turn attacks, real-world adversaries typically operate in multi-turn scenarios, iteratively probing for vulnerabilities and adapting their prompts based on threat model responses. In this paper, we propose \AlgName, a novel multi-turn red-teaming agent that emulates sophisticated human attackers through complementary learning dimensions: global tactic-wise learning that accumulates knowledge over time and generalizes to new attack goals, and local prompt-wise learning that refines implementations for specific goals when initial attempts fail. Unlike previous multi-turn approaches that rely on fixed strategy sets, \AlgName enables the agent to identify new jailbreak tactics, develop a goal-based tactic selection framework, and refine prompt formulations for selected tactics. Empirical evaluations on JailbreakBench demonstrate our framework's superior performance, achieving over 90\% attack success rates against GPT-3.5-Turbo and Llama-3.1-70B within 5 conversation turns, outperforming state-of-the-art baselines. These results highlight the effectiveness of dynamic learning in identifying and exploiting model vulnerabilities in realistic multi-turn scenarios.

Inference-time safety methods for large language models have proliferated, yet no systematic comparison exists. We evaluate five defense paradigms (no defense, static steering, CAST, AlphaSteer, probe-gated) across seven instruction-tuned models (7-31B) and five attack types (GCG, AutoDAN, DeepInception, prefilling, intent laundering). Our central finding: prompt-time activation defenses are structurally blind to prefilling attacks. AlphaSteer achieves 0% attack success on GCG, AutoDAN, and intent laundering but 50% on prefilling. We prove a corollary: any defense that gates intervention on a single layer's activation alignment with a benign reference (cone, subspace, or null-space) is blind to attacks that craft activations to lie inside that reference, whether checked at prompt time or per token. As its constructive contrapositive we introduce response-time probing: a linear probe on the model's hidden state at the first generated tokens, with AUROC 0.97-1.00 across all seven models. Combined with a halt, it cuts prefilling attack success to 0/40 on every model with 0% benign false positives, outperforming Llama Guard 3. Cross-template generalisation depends on probe depth, so we scope the claim to the canonical prefilling-template family. Composing the response-halt with AlphaSteer's null-space steering gives an orthogonal split (the halt catches prefilling, AlphaSteer catches semantic attacks), reaching defense success 0.983 on Mistral and 0.994 on Llama and dominating both components. We further show MMLU fails to capture steering's true utility cost, which appears as behavioral hedging rather than factual loss, and that diverse negative training sets cut probe false positives from 80-100% to near zero. Code, attacks, per-sample results, and the judge prompt are released.

Retrieval-Augmented Generation (RAG) systems, widely used to improve the factual grounding of large language models (LLMs), are increasingly vulnerable to poisoning attacks, where adversaries inject manipulated content into the retriever's corpus. While prior research has predominantly focused on single-attacker settings, real-world scenarios often involve multiple, competing attackers with conflicting objectives. In this work, we introduce PoisonArena, the first benchmark to systematically study and evaluate competing poisoning attacks in RAG. We formalize the multi-attacker threat model, where attackers vie to control the answer to the same query using mutually exclusive misinformation. PoisonArena leverages the Bradley-Terry model to quantify each method's competitive effectiveness in such adversarial environments. Through extensive experiments on the Natural Questions and MS MARCO datasets, we demonstrate that many attack strategies successful in isolation fail under competitive pressure. Our findings highlight the limitations of conventional evaluation metrics like Attack Success Rate (ASR) and F1 score and underscore the need for competitive evaluation to assess real-world attack robustness. PoisonArena provides a standardized framework to benchmark and develop future attack and defense strategies under more realistic, multi-adversary conditions.

Accurately evaluating adversarial robustness is a longstanding challenge. A flawed attack design can inflate robustness estimates, making deployment risk assessment and defense comparison unreliable. Historically, standardized attacks such as AutoAttack have largely resolved this for image classifiers, providing a reliable evaluation baseline for systematic comparison across defenses. However, no equivalent exists for LLM jailbreak evaluation yet, where designing such an attack is considerably more difficult. A reliable attack must, among other things, be black-box compatible, applicable to arbitrary defense pipelines, and efficient, which no existing method jointly satisfies. We introduce Indirect Harm Optimization (IHO), a masked diffusion language model attacker trained via iterative preference optimization against a harmfulness judge, requiring only black-box access to the target. The same method can be used without modification as a strong adaptive attack on individual behaviors, or as an efficient amortized policy that transfers to held-out behaviors and unseen target models without fine-tuning. Even against layered defenses, such as a Circuit Breaker-trained model combined with an auxiliary detector, IHO improves attack success considerably over state-of-the-art approaches, without any defense-specific adaptation. Our results position IHO as a practical step toward the kind of standardized jailbreak evaluation that has improved reliability in the past. Code and models are available on GitHub and Hugging Face.

Backdoor poisoning attacks add poisoned examples to otherwise-clean finetuning data, pairing a trigger with a target behavior that the model learns to produce when the trigger appears. Existing evaluations typically fix the number of poisoned examples and sample them at random from a candidate pool. We show that this can severely underestimate worst-case vulnerability: across three LLaMA-3-8B backdoor settings, holding the model, clean data, and poison count fixed, attack success ranges from 3% to 80% depending only on which poison set is chosen. We formalize poison selection as oracle-budgeted set optimization and introduce SAILS (Set-level Audit-Informed Iterative Learned Selection), which learns a set scorer from a few hundred finetune-and-evaluate runs, ranks millions of candidate sets, and audits only a small shortlist. SAILS improves held-out attack success by 30 percentage points on average over the strongest influence baselines, transfers from small-scale to full-scale finetuning, and extends to code-generation, agentic, and API-only backdoors.

Smart contract vulnerabilities have led to billions in losses, yet finding actionable exploits remains challenging. Traditional fuzzers rely on rigid heuristics and struggle with complex attacks, while human auditors are thorough but slow and don't scale. Large Language Models offer a promising middle ground, combining human-like reasoning with machine speed. Early studies show that simply prompting LLMs generates unverified vulnerability speculations with high false positive rates. To address this, we present A1, an agentic system that transforms any LLM into an end-to-end exploit generator. A1 provides agents with six domain-specific tools for autonomous vulnerability discovery, from understanding contract behavior to testing strategies on real blockchain states. All outputs are concretely validated through execution, ensuring only profitable proof-of-concept exploits are reported. We evaluate A1 across 36 real-world vulnerable contracts on Ethereum and Binance Smart Chain. A1 achieves a 63% success rate on the VERITE benchmark. Across all successful cases, A1 extracts up to \8.59 million per exploit and 9.33 million total. Using Monte Carlo analysis of historical attacks, we demonstrate that immediate vulnerability detection yields 86-89% success probability, dropping to 6-21% with week-long delays. Our economic analysis reveals a troubling asymmetry: attackers achieve profitability at \6,000 exploit values while defenders require 60,000 -- raising fundamental questions about whether AI agents inevitably favor exploitation over defense.

To ensure AI safety, instruction-tuned Large Language Models (LLMs) are specifically trained to ensure alignment, which refers to making models behave in accordance with human intentions. While these models have demonstrated commendable results on various safety benchmarks, the vulnerability of their safety alignment has not been extensively studied. This is particularly troubling given the potential harm that LLMs can inflict. Existing attack methods on LLMs often rely on poisoned training data or the injection of malicious prompts. These approaches compromise the stealthiness and generalizability of the attacks, making them susceptible to detection. Additionally, these models often demand substantial computational resources for implementation, making them less practical for real-world applications. Inspired by recent success in modifying model behavior through steering vectors without the need for optimization, and drawing on its effectiveness in red-teaming LLMs, we conducted experiments employing activation steering to target four key aspects of LLMs: truthfulness, toxicity, bias, and harmfulness - across a varied set of attack settings. To establish a universal attack strategy applicable to diverse target alignments without depending on manual analysis, we automatically select the intervention layer based on contrastive layer search. Our experiment results show that activation attacks are highly effective and add little or no overhead to attack efficiency. Additionally, we discuss potential countermeasures against such activation attacks. Our code and data are available at https://github.com/wang2226/Backdoor-Activation-Attack Warning: this paper contains content that can be offensive or upsetting.

Red-teaming has been a widely adopted way to evaluate the harmfulness of Large Language Models (LLMs). It aims to jailbreak a model's safety behavior to make it act as a helpful agent disregarding the harmfulness of the query. Existing methods are primarily based on input text-based red-teaming such as adversarial prompts, low-resource prompts, or contextualized prompts to condition the model in a way to bypass its safe behavior. Bypassing the guardrails uncovers hidden harmful information and biases in the model that are left untreated or newly introduced by its safety training. However, prompt-based attacks fail to provide such a diagnosis owing to their low attack success rate, and applicability to specific models. In this paper, we present a new perspective on LLM safety research i.e., parametric red-teaming through Unalignment. It simply (instruction) tunes the model parameters to break model guardrails that are not deeply rooted in the model's behavior. Unalignment using as few as 100 examples can significantly bypass commonly referred to as CHATGPT, to the point where it responds with an 88% success rate to harmful queries on two safety benchmark datasets. On open-source models such as VICUNA-7B and LLAMA-2-CHAT 7B AND 13B, it shows an attack success rate of more than 91%. On bias evaluations, Unalignment exposes inherent biases in safety-aligned models such as CHATGPT and LLAMA- 2-CHAT where the model's responses are strongly biased and opinionated 64% of the time.

Proactive personal agents increasingly decide what to recommend, how to personalize advice, and what follow-up assistance to offer, creating a new user-decision attack surface for provider-side indirect prompt injection. We show that an external provider need not access private user context, compromise the agent, or gain additional permissions: by controlling only content associated with its own target, it can redirect an otherwise benign agent to advance that target, recruit legitimately available user context to justify it, and proactively reduce the friction of adoption. We characterize this failure mode through Target Control, Private Binding, and Prospective Support, which respectively steer what the agent advances, how it connects the target to the user, and what target-specific assistance it offers next. Across three proactive-agent environments and six simulated user models, the full attack increases target authorization in all tested environment-user-model combinations, with a macro gain of up to 77.4 percentage points. Controlled replay shows that correct user-target binding is more consequential than additional proposal detail alone, while a multi-turn extension reveals that provider objectives can remain influential even without final authorization by reshaping how the agent responds to user constraints and resistance. These findings expose a broader trust boundary: capabilities designed to serve the user can be redirected toward objectives originating outside the user-agent relationship.

State-of-the-art membership inference attacks (MIAs) typically require training many reference models, making it difficult to scale these attacks to large pre-trained language models (LLMs). As a result, prior research has either relied on weaker attacks that avoid training reference models (e.g., fine-tuning attacks), or on stronger attacks applied to small-scale models and datasets. However, weaker attacks have been shown to be brittle - achieving close-to-arbitrary success - and insights from strong attacks in simplified settings do not translate to today's LLMs. These challenges have prompted an important question: are the limitations observed in prior work due to attack design choices, or are MIAs fundamentally ineffective on LLMs? We address this question by scaling LiRA - one of the strongest MIAs - to GPT-2 architectures ranging from 10M to 1B parameters, training reference models on over 20B tokens from the C4 dataset. Our results advance the understanding of MIAs on LLMs in three key ways: (1) strong MIAs can succeed on pre-trained LLMs; (2) their effectiveness, however, remains limited (e.g., AUC<0.7) in practical settings; and, (3) the relationship between MIA success and related privacy metrics is not as straightforward as prior work has suggested.

Red teaming must continually adapt as frontier LLM safeguards evolve, yet existing approaches largely search for adversarial prompts or optimize within fixed attack procedures. We observe that even when an attack becomes ineffective, its underlying mechanisms can remain useful and can be revised or recombined to construct stronger attacks. Based on this insight, we introduce RedDarwin, an agentic framework that shifts the unit of jailbreak evolution from prompts and fixed attacks to executable attack skills. RedDarwin consists of 47 reusable base skills and autonomously revises, composes, executes, and selects them using target-model feedback, allowing successful discoveries to become building blocks for subsequent evolution. RedDarwin produces 65 evolved skills, improving 44 of 47 base attacks and increasing their mean attack success rate (ASR) on AdvBench from 18.8% to 47.3%. These evolved skills consistently outperform baselines on the held-out StrongREJECT and frontier LLMs unseen during evolution; with only 10 target-model queries, RedDarwin achieves 100% ASR on GPT-5.6-Sol, 92% on Claude-Sonnet-5, and 80% on Gemini-3.8-Flash. Analysis of the evolution trajectories further shows that strong attacks often emerge from novel combinations of reusable mechanisms rather than from individually dominant ones. We believe this paradigm can accelerate adaptive red teaming and inform stronger safeguards, creating complementary value for both safety evaluation and defense.

As Large Language Models (LLMs) increasingly serve as primary knowledge retrieval interfaces, their robustness against persuasion attacks---attempts to inject misinformation or enforce counterfactuals---has become a critical safety concern. Existing red-teaming frameworks typically evaluate models in multi-turn dialogues where the target model retains full conversation history. We identify a critical flaw in this setting termed ``Refusal Inertia'': a model's initial refusal often propagates through subsequent turns largely to maintain contextual consistency, thereby masking its true vulnerability to sophisticated, isolated persuasion attempts. To rigorously evaluate the ``cold-start'' defense capabilities of SOTA models, we introduce the SAST-IR (Stateful Attacker, Stateless Target - Iterative Refinement) framework. By enforcing a memory wipe on the target while retaining the attacker's history, we simulate a worst-case adversarial setting using multi-turn (stateless) iterations. Leveraging CP-Agent (Cognitive Persuasion Agent), an enhanced diagnosis-guided agent, our experiments on the custom CounterFact-Strict dataset (N=50) yield alarming results: simple, diverse attack strategies achieved a staggering 96\% success rate, exposing severe brittleness in memory-less defense. Furthermore, we reveal a ``Complexity Paradox'': while complex, iteratively refined attacks are effective, they often trigger defensive compliance, whereas simple strategies achieve a higher rate of genuine persuasion (84.7\%). Our code and dataset are available at GitHub, https://github.com/cza1006/llm-persuasion-defense.

Leading language model (LM) providers like OpenAI and Google offer fine-tuning APIs that allow customers to adapt LMs for specific use cases. To prevent misuse, these LM providers implement filtering mechanisms to block harmful fine-tuning data. Consequently, adversaries seeking to produce unsafe LMs via these APIs must craft adversarial training data that are not identifiably harmful. We make three contributions in this context: 1. We show that many existing attacks that use harmless data to create unsafe LMs rely on eliminating model refusals in the first few tokens of their responses. 2. We show that such prior attacks can be blocked by a simple defense that pre-fills the first few tokens from an aligned model before letting the fine-tuned model fill in the rest. 3. We describe a new data-poisoning attack, ``No, Of course I Can Execute'' (NOICE), which exploits an LM's formulaic refusal mechanism to elicit harmful responses. By training an LM to refuse benign requests on the basis of safety before fulfilling those requests regardless, we are able to jailbreak several open-source models and a closed-source model (GPT-4o). We show an attack success rate (ASR) of 57% against GPT-4o; our attack earned a Bug Bounty from OpenAI. Against open-source models protected by simple defenses, we improve ASRs by an average of 3.25 times compared to the best performing previous attacks that use only harmless data. NOICE demonstrates the exploitability of repetitive refusal mechanisms and broadens understanding of the threats closed-source models face from harmless data.

The safety of large language models (LLMs) has garnered significant research attention. In this paper, we argue that previous empirical studies demonstrate LLMs exhibit a propensity to trust information from authoritative sources, such as academic papers, implying new possible vulnerabilities. To verify this possibility, a preliminary analysis is designed to illustrate our two findings. Based on this insight, a novel jailbreaking method, Paper Summary Attack (PSA), is proposed. It systematically synthesizes content from either attack-focused or defense-focused LLM safety paper to construct an adversarial prompt template, while strategically infilling harmful query as adversarial payloads within predefined subsections. Extensive experiments show significant vulnerabilities not only in base LLMs, but also in state-of-the-art reasoning model like Deepseek-R1. PSA achieves a 97\% attack success rate (ASR) on well-aligned models like Claude3.5-Sonnet and an even higher 98\% ASR on Deepseek-R1. More intriguingly, our work has further revealed diametrically opposed vulnerability bias across different base models, and even between different versions of the same model, when exposed to either attack-focused or defense-focused papers. This phenomenon potentially indicates future research clues for both adversarial methodologies and safety alignment.Code is available at https://github.com/233liang/Paper-Summary-Attack

This paper analyzes Large Language Model (LLM) security vulnerabilities based on data from Crucible, encompassing 214,271 attack attempts by 1,674 users across 30 LLM challenges. Our findings reveal automated approaches significantly outperform manual techniques (69.5% vs 47.6% success rate), despite only 5.2% of users employing automation. We demonstrate that automated approaches excel in systematic exploration and pattern matching challenges, while manual approaches retain speed advantages in certain creative reasoning scenarios, often solving problems 5x faster when successful. Challenge categories requiring systematic exploration are most effectively targeted through automation, while intuitive challenges sometimes favor manual techniques for time-to-solve metrics. These results illuminate how algorithmic testing is transforming AI red-teaming practices, with implications for both offensive security research and defensive measures. Our analysis suggests optimal security testing combines human creativity for strategy development with programmatic execution for thorough exploration.

Control evaluations measure whether monitoring and security protocols for AI systems prevent intentionally subversive AI models from causing harm. Our work presents the first control evaluation performed in an agent environment. We construct BashBench, a dataset of 257 challenging multi-step system administration tasks, and evaluate whether various safety measures can prevent an adversarially constructed AI agent from covertly downloading and executing malicious code in this environment. This multi-step setting introduces new attack and defense dynamics, which we investigate in order to design novel control protocols that prevent safety failures without hindering the ability of non-malicious agents to perform useful work. We introduce a class of control protocols called resample protocols that dynamically take additional samples of certain actions. We find these protocols significantly improve on existing techniques by selectively blocking the AI agent from executing suspicious code and incriminating the agent by generating additional examples of dangerous behavior. We measure the tradeoff between attack prevention and usefulness; our best protocol combines resampling with analysis of previous steps, reducing the success rate of attacks from 58% to 7% at a 5% cost to the performance of a non-malicious agent.

The autonomous AI agents using large language models can create undeniable values in all span of the society but they face security threats from adversaries that warrants immediate protective solutions because trust and safety issues arise. Considering the many-shot jailbreaking and deceptive alignment as some of the main advanced attacks, that cannot be mitigated by the static guardrails used during the supervised training, points out a crucial research priority for real world robustness. The combination of static guardrails in dynamic multi-agent system fails to defend against those attacks. We intend to enhance security for LLM-based agents through the development of new evaluation frameworks which identify and counter threats for safe operational deployment. Our work uses three examination methods to detect rogue agents through a Reverse Turing Test and analyze deceptive alignment through multi-agent simulations and develops an anti-jailbreaking system by testing it with GEMINI 1.5 pro and llama-3.3-70B, deepseek r1 models using tool-mediated adversarial scenarios. The detection capabilities are strong such as 94\% accuracy for GEMINI 1.5 pro yet the system suffers persistent vulnerabilities when under long attacks as prompt length increases attack success rates (ASR) and diversity metrics become ineffective in prediction while revealing multiple complex system faults. The findings demonstrate the necessity of adopting flexible security systems based on active monitoring that can be performed by the agents themselves together with adaptable interventions by system admin as the current models can create vulnerabilities that can lead to the unreliable and vulnerable system. So, in our work, we try to address such situations and propose a comprehensive framework to counteract the security issues.

As the capabilities of large language models continue to advance, so does their potential for misuse. While closed-source models typically rely on external defenses, open-weight models must primarily depend on internal safeguards to mitigate harmful behavior. Prior red-teaming research has largely focused on input-based jailbreaking and parameter-level manipulations. However, open-weight models also natively support prefilling, which allows an attacker to predefine initial response tokens before generation begins. Despite its potential, this attack vector has received little systematic attention. We present the largest empirical study to date of prefill attacks, evaluating over 20 existing and novel strategies across multiple model families and state-of-the-art open-weight models. Our results show that prefill attacks are consistently effective against all major contemporary open-weight models, revealing a critical and previously underexplored vulnerability with significant implications for deployment. While certain large reasoning models exhibit some robustness against generic prefilling, they remain vulnerable to tailored, model-specific strategies. Our findings underscore the urgent need for model developers to prioritize defenses against prefill attacks in open-weight LLMs.

Large language model (LLM) systems increasingly power everyday AI applications such as chatbots, computer-use assistants, and autonomous robots, where performance often depends on manually well-crafted prompts. LLM-based prompt optimizers reduce that effort by iteratively refining prompts from scored feedback, yet the security of this optimization stage remains underexamined. We present the first systematic analysis of poisoning risks in LLM-based prompt optimization. Using HarmBench, we find systems are substantially more vulnerable to manipulated feedback than to query poisoning alone: feedback-based attacks raise attack success rate (ASR) by up to ΔASR = 0.48. We introduce a simple fake reward attack that requires no access to the reward model and significantly increases vulnerability. We also propose a lightweight highlighting defense that reduces the fake reward ΔASR from 0.23 to 0.07 without degrading utility. These results establish prompt optimization pipelines as a first-class attack surface and motivate stronger safeguards for feedback channels and optimization frameworks.

Large language models have seen widespread adoption, yet they remain vulnerable to multi-turn jailbreak attacks, threatening their safe deployment. This has led to the task of training automated multi-turn attackers to probe model safety vulnerabilities. However, existing approaches typically rely on turn-level optimization, which is insufficient for learning long-term attack strategies. To bridge this gap, we formulate this task as a multi-turn reinforcement learning problem, directly optimizing the harmfulness of the final-turn response as the outcome reward. To address the sparse supervision of the outcome reward, we introduce TROJail, which employs two process rewards to evaluate the utility of intermediate prompts and integrate them into advantage estimation. These rewards (1) penalize overly harmful prompts that trigger the model's refusal mechanism, and (2) encourage steering the semantic relevance of responses toward the targeted harmful content. Experimental results show improved attack success rates across multiple models and benchmarks, highlighting the effectiveness of our approach. The code is available at https://github.com/xxiqiao/TROJail. Warning: This paper contains examples of harmful content.

This paper addresses a critical challenge in cybersecurity: the gap between vulnerability information represented by Common Vulnerabilities and Exposures (CVEs) and the resulting cyberattack actions. CVEs provide insights into vulnerabilities, but often lack details on potential threat actions (tactics, techniques, and procedures, or TTPs) within the ATT&CK framework. This gap hinders accurate CVE categorization and proactive countermeasure initiation. The paper introduces the TTPpredictor tool, which uses innovative techniques to analyze CVE descriptions and infer plausible TTP attacks resulting from CVE exploitation. TTPpredictor overcomes challenges posed by limited labeled data and semantic disparities between CVE and TTP descriptions. It initially extracts threat actions from unstructured cyber threat reports using Semantic Role Labeling (SRL) techniques. These actions, along with their contextual attributes, are correlated with MITRE's attack functionality classes. This automated correlation facilitates the creation of labeled data, essential for categorizing novel threat actions into threat functionality classes and TTPs. The paper presents an empirical assessment, demonstrating TTPpredictor's effectiveness with accuracy rates of approximately 98% and F1-scores ranging from 95% to 98% in precise CVE classification to ATT&CK techniques. TTPpredictor outperforms state-of-the-art language model tools like ChatGPT. Overall, this paper offers a robust solution for linking CVEs to potential attack techniques, enhancing cybersecurity practitioners' ability to proactively identify and mitigate threats.

How should we evaluate the robustness of language model defenses? Current defenses against jailbreaks and prompt injections (which aim to prevent an attacker from eliciting harmful knowledge or remotely triggering malicious actions, respectively) are typically evaluated either against a static set of harmful attack strings, or against computationally weak optimization methods that were not designed with the defense in mind. We argue that this evaluation process is flawed. Instead, we should evaluate defenses against adaptive attackers who explicitly modify their attack strategy to counter a defense's design while spending considerable resources to optimize their objective. By systematically tuning and scaling general optimization techniques-gradient descent, reinforcement learning, random search, and human-guided exploration-we bypass 12 recent defenses (based on a diverse set of techniques) with attack success rate above 90% for most; importantly, the majority of defenses originally reported near-zero attack success rates. We believe that future defense work must consider stronger attacks, such as the ones we describe, in order to make reliable and convincing claims of robustness.

Jailbreaking is an essential adversarial technique for red-teaming these models to uncover and patch security flaws. However, existing jailbreak methods face significant drawbacks. Token-level jailbreak attacks often produce incoherent or unreadable inputs and exhibit poor transferability, while prompt-level attacks lack scalability and rely heavily on manual effort and human ingenuity. We propose a concise and effective two-stage framework that combines the advantages of these approaches. The first stage performs a scenario-based generation of context and rephrases the original malicious query to obscure its harmful intent. The second stage then utilizes information from the model's hidden states to guide fine-grained edits, effectively steering the model's internal representation of the input from a malicious toward a benign one. Extensive experiments demonstrate that this method achieves state-of-the-art Attack Success Rate, with gains of up to 37.74% over the strongest baseline, and exhibits excellent transferability to black-box models. Our analysis further demonstrates that AGILE maintains substantial effectiveness against prominent defense mechanisms, highlighting the limitations of current safeguards and providing valuable insights for future defense development. Our code is available at https://github.com/yunsaijc/AGILE.

Self-hosted AI agents read and write their own memory and configuration files to function. An agent may get compromised via corruption of its own state -- a compromise realized via legitimate OS system call invocation. We refer to this class of threats as self-state attacks. In this paper, we investigate the OS resilience to this class of attacks. Formally, we characterize a four-axis attack space (Target, Mechanism, Granularity, Temporal); investigate the structural limits of prevention, detection, and recovery; and introduce a workload-conditioned view of detectability. To instantiate the framework, we collect live activity traces from a representative self-hosted agent running across distinct workload profiles, and realize the attack space as a 23-cell matrix, 43 concrete operations on real self-state files, and injected into those traces. We then evaluate both canonical and workload-conditioned defense strategies. The empirical results show that a layered defense stack (access-control prevention on the instruction and configuration layers, workload-conditioned detection on the memory layer, and periodic backup for recovery) is effective on most attack cells while a small residual attack surface remains structurally indistinguishable at the OS level. These findings suggest that against the newly established class of self-state attacks, OS-level defense needs to be reconsidered, potentially opening new research directions in the field.

With the recent surge in popularity of LLMs has come an ever-increasing need for LLM safety training. In this paper, we investigate the fragility of SOTA open-source LLMs under simple, optimization-free attacks we refer to as priming attacks, which are easy to execute and effectively bypass alignment from safety training. Our proposed attack improves the Attack Success Rate on Harmful Behaviors, as measured by Llama Guard, by up to 3.3times compared to baselines. Source code and data are available at https://github.com/uiuc-focal-lab/llm-priming-attacks.

Developers can build LLM agents by adapting third-party models through benign post-training. We study a supply-chain threat in which an attacker supplies a model with a backdoor: hidden behavior that produces malicious outputs when a particular input pattern appears. Focusing on software-engineering agents, we ask whether such backdoors survive the developer's supervised fine-tuning (SFT) and subsequent task-level reinforcement learning (RL). We observe that benign SFT substantially reduces attack success, but subsequent RL often preserves the residual behavior and sometimes even increases attack success. Our analysis of backdoor erosion during SFT identifies two factors that may favor survival: initial backdoor strength and gradient compatibility with benign training. These factors motivate PersistBD, which refines an already-backdoored model before release to improve its persistency through the benign post-training process. On Qwen2.5-Coder-7B, PersistBD raises attack success from 20% to 74% after SFT and from 20% to 76% after SFT-RL, while maintaining comparable benign task performance. Together, our results show that backdoors can remain active through benign post-training and that adversaries can deliberately increase their persistence. This highlights a supply-chain risk for AI developers and motivates stronger techniques for detecting and mitigating inherited backdoors when adapting third-party models into agents. Our code is available at https://github.com/uiuc-kang-lab/PersistBD.

Recent work has shown it is possible to construct adversarial examples that cause an aligned language model to emit harmful strings or perform harmful behavior. Existing attacks work either in the white-box setting (with full access to the model weights), or through transferability: the phenomenon that adversarial examples crafted on one model often remain effective on other models. We improve on prior work with a query-based attack that leverages API access to a remote language model to construct adversarial examples that cause the model to emit harmful strings with (much) higher probability than with transfer-only attacks. We validate our attack on GPT-3.5 and OpenAI's safety classifier; we can cause GPT-3.5 to emit harmful strings that current transfer attacks fail at, and we can evade the safety classifier with nearly 100% probability.

Red-teaming, or identifying prompts that elicit harmful responses, is a critical step in ensuring the safe and responsible deployment of large language models (LLMs). Developing effective protection against many modes of attack prompts requires discovering diverse attacks. Automated red-teaming typically uses reinforcement learning to fine-tune an attacker language model to generate prompts that elicit undesirable responses from a target LLM, as measured, for example, by an auxiliary toxicity classifier. We show that even with explicit regularization to favor novelty and diversity, existing approaches suffer from mode collapse or fail to generate effective attacks. As a flexible and probabilistically principled alternative, we propose to use GFlowNet fine-tuning, followed by a secondary smoothing phase, to train the attacker model to generate diverse and effective attack prompts. We find that the attacks generated by our method are effective against a wide range of target LLMs, both with and without safety tuning, and transfer well between target LLMs. Finally, we demonstrate that models safety-tuned using a dataset of red-teaming prompts generated by our method are robust to attacks from other RL-based red-teaming approaches.

Large Language Models (LLMs) have enabled agents to move beyond conversation toward end-to-end task execution and become more helpful. However, this helpfulness introduces new security risks stem less from direct interface abuse than from acting on user-provided content. Existing studies on agent security largely focus on model-internal vulnerabilities or adversarial access to agent interfaces, overlooking attacks that exploit users as unintended conduits. In this paper, we study user-mediated attacks, where benign users are tricked into relaying untrusted or attacker-controlled content to agents, and analyze how commercial LLM agents respond under such conditions. We conduct a systematic evaluation of 12 commercial agents in a sandboxed environment, covering 6 trip-planning agents and 6 web-use agents, and compare agent behavior across scenarios with no, soft, and hard user-requested safety checks. Our results show that agents are too helpful to be safe by default. Without explicit safety requests, trip-planning agents bypass safety constraints in over 92% of cases, converting unverified content into confident booking guidance. Web-use agents exhibit near-deterministic execution of risky actions, with 9 out of 17 supported tests reaching a 100% bypass rate. Even when users express soft or hard safety intent, constraint bypass remains substantial, reaching up to 54.7% and 7% for trip-planning agents, respectively. These findings reveal that the primary issue is not a lack of safety capability, but its prioritization. Agents invoke safety checks only conditionally when explicitly prompted, and otherwise default to goal-driven execution. Moreover, agents lack clear task boundaries and stopping rules, frequently over-executing workflows in ways that lead to unnecessary data disclosure and real-world harm.

Current LLM safety defenses fail under decomposition attacks, where a malicious goal is decomposed into benign subtasks that circumvent refusals. The challenge lies in the existing shallow safety alignment techniques: they only detect harm in the immediate prompt and do not reason about long-range intent, leaving them blind to malicious intent that emerges over a sequence of seemingly benign instructions. We therefore propose adding an external monitor that observes the conversation at a higher granularity. To facilitate our study of monitoring decomposition attacks, we curate the largest and most diverse dataset to date, including question-answering, text-to-image, and agentic tasks. We verify our datasets by testing them on frontier LLMs and show an 87% attack success rate on average on GPT-4o. This confirms that decomposition attack is broadly effective. Additionally, we find that random tasks can be injected into the decomposed subtasks to further obfuscate malicious intents. To defend in real time, we propose a lightweight sequential monitoring framework that cumulatively evaluates each subtask. We show that a carefully prompt engineered lightweight monitor achieves a 93% defense success rate, beating reasoning models like o3 mini as a monitor. Moreover, it remains robust against random task injection and cuts cost by 90% and latency by 50%. Our findings suggest that lightweight sequential monitors are highly effective in mitigating decomposition attacks and are viable in deployment.

Adapting Large Language Models (LLMs) to specific tasks introduces concerns about computational efficiency, prompting an exploration of efficient methods such as In-Context Learning (ICL). However, the vulnerability of ICL to privacy attacks under realistic assumptions remains largely unexplored. In this work, we present the first membership inference attack tailored for ICL, relying solely on generated texts without their associated probabilities. We propose four attack strategies tailored to various constrained scenarios and conduct extensive experiments on four popular large language models. Empirical results show that our attacks can accurately determine membership status in most cases, e.g., 95\% accuracy advantage against LLaMA, indicating that the associated risks are much higher than those shown by existing probability-based attacks. Additionally, we propose a hybrid attack that synthesizes the strengths of the aforementioned strategies, achieving an accuracy advantage of over 95\% in most cases. Furthermore, we investigate three potential defenses targeting data, instruction, and output. Results demonstrate combining defenses from orthogonal dimensions significantly reduces privacy leakage and offers enhanced privacy assurances.

AI agents often rely on persistent memory to retain user preferences and operational rules across sessions. However, this capability introduces a new safety risk: malicious instructions from messages, documents, or Web content can be retained in memory and influence future tasks even after the original attack content is removed. Existing attack success metrics, however, fail to capture who is affected and how attacks translate into downstream harm during otherwise normal task execution. We introduce MemHarmBench, a victim-centric benchmark for evaluating cross-session prompt injection in memory-persistent AI agents. MemHarmBench considers three categories of potential victims: users, workspace/project owners, and external stakeholders. Our evaluation first exposes an agent to malicious instructions and tests whether they are retained in memory. We then remove the attack content and initiate a new session with a legitimate task while preserving the agent's memory. We jointly evaluate whether the agent follows the attacker's intent, completes the legitimate task, and exhibits observable execution anomalies. Across multiple agent systems, we find that cross-session attacks can remain behaviorally stealthy: agents often complete tasks normally and exhibit no detectable anomalies while still making critical decisions aligned with the attacker's intent. By connecting malicious memory retention to downstream decisions and affected parties, MemHarmBench provides a systematic framework for exposing safety risks that conventional attack- and task-success metrics may overlook. We publicly release MemHarmBench at https://github.com/Kirito14IT/MemHarmBench.

Clarification-seeking behavior is widely regarded as a desirable property of LLM agents, enabling them to resolve ambiguity before acting on underspecified tasks. However, the security implications of this interaction pattern remain unexplored. We investigate whether the transition from standard execution to a clarification-seeking state increases an agent's susceptibility to prompt injection attacks. We introduce ASPI (Ambiguous-State Prompt Injection), a benchmark of 728 task-attack scenarios that isolates clarification as a distinct agent state and measures how this state transition affects vulnerability under controlled conditions. Each benchmark instance is evaluated under matched execution and clarification settings: in the execution setting, the agent acts on a fully specified instruction and encounters adversarial content only through tool-returned data; in the clarification setting, the agent must first request and incorporate additional user input before acting. We evaluate ten frontier LLMs and find that clarification-seeking consistently and substantially amplifies vulnerability. For instance, attack success rises from 1.8% to 34.0% for o3 and from 2.2% to 35.7% for Gemini-3-Flash. A decomposition analysis reveals that this gap reflects both a state-dependent shift in how models process incoming content and a channel-specific effect arising from the agent-solicited clarification interface. These findings demonstrate that standard execution-time security evaluation systematically underestimates the attack surface of interactive agents, and that robustness under fully specified tasks does not translate to robustness under ambiguity. For reproducibility, our data and source code are available at https://github.com/scaleapi/aspi.

Large language models (LLMs) introduce new security risks, but there are few comprehensive evaluation suites to measure and reduce these risks. We present BenchmarkName, a novel benchmark to quantify LLM security risks and capabilities. We introduce two new areas for testing: prompt injection and code interpreter abuse. We evaluated multiple state-of-the-art (SOTA) LLMs, including GPT-4, Mistral, Meta Llama 3 70B-Instruct, and Code Llama. Our results show that conditioning away risk of attack remains an unsolved problem; for example, all tested models showed between 26% and 41% successful prompt injection tests. We further introduce the safety-utility tradeoff: conditioning an LLM to reject unsafe prompts can cause the LLM to falsely reject answering benign prompts, which lowers utility. We propose quantifying this tradeoff using False Refusal Rate (FRR). As an illustration, we introduce a novel test set to quantify FRR for cyberattack helpfulness risk. We find many LLMs able to successfully comply with "borderline" benign requests while still rejecting most unsafe requests. Finally, we quantify the utility of LLMs for automating a core cybersecurity task, that of exploiting software vulnerabilities. This is important because the offensive capabilities of LLMs are of intense interest; we quantify this by creating novel test sets for four representative problems. We find that models with coding capabilities perform better than those without, but that further work is needed for LLMs to become proficient at exploit generation. Our code is open source and can be used to evaluate other LLMs.

Large Language Models (LLMs) are typically evaluated for safety under single-shot or low-budget adversarial prompting, which underestimates real-world risk. In practice, attackers can exploit large-scale parallel sampling to repeatedly probe a model until a harmful response is produced. While recent work shows that attack success increases with repeated sampling, principled methods for predicting large-scale adversarial risk remain limited. We propose a scaling-aware Best-of-N estimation of risk, SABER, for modeling jailbreak vulnerability under Best-of-N sampling. We model sample-level success probabilities using a Beta distribution, the conjugate prior of the Bernoulli distribution, and derive an analytic scaling law that enables reliable extrapolation of large-N attack success rates from small-budget measurements. Using only n=100 samples, our anchored estimator predicts ASR@1000 with a mean absolute error of 1.66, compared to 12.04 for the baseline, which is an 86.2% reduction in estimation error. Our results reveal heterogeneous risk scaling profiles and show that models appearing robust under standard evaluation can experience rapid nonlinear risk amplification under parallel adversarial pressure. This work provides a low-cost, scalable methodology for realistic LLM safety assessment. We will release our code and evaluation scripts upon publication to future research.

Large language models (LLMs) are susceptible to red teaming attacks, which can induce LLMs to generate harmful content. Previous research constructs attack prompts via manual or automatic methods, which have their own limitations on construction cost and quality. To address these issues, we propose an integrated approach that combines manual and automatic methods to economically generate high-quality attack prompts. Specifically, considering the impressive capabilities of newly emerged LLMs, we propose an attack framework to instruct LLMs to mimic human-generated prompts through in-context learning. Furthermore, we propose a defense framework that fine-tunes victim LLMs through iterative interactions with the attack framework to enhance their safety against red teaming attacks. Extensive experiments on different LLMs validate the effectiveness of our proposed attack and defense frameworks. Additionally, we release a series of attack prompts datasets named SAP with varying sizes, facilitating the safety evaluation and enhancement of more LLMs. Our code and dataset is available on https://github.com/Aatrox103/SAP .

As language models take on agentic roles that span calling external APIs, reading tool outputs, and acting on instructions embedded in third-party content, their attack surface expands well beyond what users type. Whether a model treats a malicious instruction the same way regardless of where it arrives has not been systematically studied. We introduce the Safety Asymmetry Score (SAS), which measures how much a model's susceptibility to adversarial content shifts depending on whether that content arrives in the user message, tool metadata, or tool output, using matched payload pairs that keep the malicious text identical and vary only the context of delivery. Evaluated across 6 production LLMs and three attack families, we find a consistent and informative asymmetry: agent-native models are substantially more vulnerable when adversarial content arrives via tool descriptions than via user messages, while general-purpose models show the reverse. This asymmetry further inverts when the same content is delivered through tool outputs rather than descriptions, suggesting models implicitly treat tool metadata as trusted instructions and tool results as ordinary data. A mechanistic study on Llama 3.3 70B reveals that the safety-relevant representation is causally present at mid-to-late network depths but non-linearly encoded, explaining why linear probes fail to detect it. These findings expose a systematic, channel-dependent blind spot in how current tool-using models handle adversarial content.

Prompt injection attacks pose serious security risks across a wide range of real-world applications. While receiving increasing attention, the community faces a critical gap: the lack of a unified platform for prompt injection evaluation. This makes it challenging to reliably compare defenses, understand their true robustness under diverse attacks, or assess how well they generalize across tasks and benchmarks. For instance, many defenses initially reported as effective were later found to exhibit limited robustness on diverse datasets and attacks. To bridge this gap, we introduce PIArena, a unified and extensible platform for prompt injection evaluation that enables users to easily integrate state-of-the-art attacks and defenses and evaluate them across a variety of existing and new benchmarks. We also design a dynamic strategy-based attack that adaptively optimizes injected prompts based on defense feedback. Through comprehensive evaluation using PIArena, we uncover critical limitations of state-of-the-art defenses: limited generalizability across tasks, vulnerability to adaptive attacks, and fundamental challenges when an injected task aligns with the target task. The code and datasets are available at https://github.com/sleeepeer/PIArena.

Cowork agents may complete benign tasks while disclosing protected data, manipulating unauthorized state, invocate unauthorized API. We define behavioral safety and introduce ActBench, a self-evolving benchmark that evaluates such behavior risk from execution trajectories rather than final responses. Each case pairs a benign task with an adversarial variant that preserves its instruction, configuration, initial state, rating model, and trusted records while injecting a task-reachable payload. ActBench contains 600 cases from 213 scenarios, spanning 15 risk behaviors, six execution spaces, and 48 web-service APIs.To move beyond static payloads, we propose a reward-guided beam search method that jointly optimizes attack effectiveness and task utility, while reflection diagnoses failed execution checkpoint and guides payload revision. Besides, we propose a dual evidence verification mechanism that verifies agent execution safety and utility through log evidence and LLM-based trajectory evidence.We evaluate 15 LLMs and 6 open-source cowork agents over 24,000 trajectories. Under a fixed harness, attack success rates ranges from 10.1% to 94.4% across models, while under a fixed base model, they range from 73.7% to 94.4% across agents.These results show greater variation across models than agent harness, while attacks remain highly successful across all tested harnesses.Our benchmark is released at: https://github.com/zjuicsr/ActBench.

Existing language model safety evaluations focus on overt attacks and low-stakes tasks. In reality, an attacker can easily subvert existing safeguards by requesting help on small, benign-seeming tasks across many independent queries. Because the individual queries do not appear harmful, the attack is hard to detect. However, when combined, these fragments uplift misuse by helping the attacker complete hard and dangerous tasks. Toward identifying defenses against such strategies, we develop Benchmarks for Stateful Defenses (BSD), a data generation pipeline that automates evaluations of covert attacks and corresponding defenses. Using this pipeline, we curate two new datasets that are consistently refused by frontier models and are too difficult for weaker open-weight models. This enables us to evaluate decomposition attacks, which are found to be effective misuse enablers, and to highlight stateful defenses as a promising countermeasure.

While recent advancements in large language model (LLM) alignment have enabled the effective identification of malicious objectives involving scene nesting and keyword rewriting, our study reveals that these methods remain inadequate at detecting malicious objectives expressed through context within nested harmless objectives. This study identifies a previously overlooked vulnerability, which we term Attack via Implicit Reference (AIR). AIR decomposes a malicious objective into permissible objectives and links them through implicit references within the context. This method employs multiple related harmless objectives to generate malicious content without triggering refusal responses, thereby effectively bypassing existing detection techniques.Our experiments demonstrate AIR's effectiveness across state-of-the-art LLMs, achieving an attack success rate (ASR) exceeding 90% on most models, including GPT-4o, Claude-3.5-Sonnet, and Qwen-2-72B. Notably, we observe an inverse scaling phenomenon, where larger models are more vulnerable to this attack method. These findings underscore the urgent need for defense mechanisms capable of understanding and preventing contextual attacks. Furthermore, we introduce a cross-model attack strategy that leverages less secure models to generate malicious contexts, thereby further increasing the ASR when targeting other models.Our code and jailbreak artifacts can be found at https://github.com/Lucas-TY/llm_Implicit_reference.

The model context protocol (MCP) standardizes how LLMs connect to external tools and data sources, enabling faster integration but introducing new attack vectors. Despite the growing adoption of MCP, existing MCP security studies classify attacks by their observable effects, obscuring how attacks behave across different MCP server components and overlooking multi-component attack chains. Meanwhile, existing defenses are less effective when facing multi-component attacks or previously unknown malicious behaviors. This work presents a component-centric perspective for understanding and detecting malicious MCP servers. First, we build the first component-centric PoC dataset of 114 malicious MCP servers where attacks are achieved as manipulation over MCP components and their compositions. We evaluate these attacks' effectiveness across two MCP hosts and five LLMs, and uncover that (1) component position shapes attack success rate; and (2) multi-component compositions often outperform single-component attacks by distributing malicious logic. Second, we propose and implement Connor, a two-stage behavioral deviation detector for malicious MCP servers. It first performs pre-execution analysis to detect malicious shell commands and extract each tool's function intent, and then conducts step-wise in-execution analysis to trace each tool's behavioral trajectories and detect deviations from its function intent. Evaluation on our curated dataset indicates that Connor achieves an F1-score of 94.6%, outperforming the state of the art by 8.9% to 59.6%. In real-world detection, Connor identifies two malicious servers.

We study how runtime enforcement against unsafe actions affects end-to-end task performance in multi-step tool using large language model (LLM) agents. Using tau-bench across Airline and Retail domains, we compare baseline Tool-Calling, planning-integrated (TRIAD), and policy-mediated (TRIAD-SAFETY) architectures with GPT-OSS-20B and GLM-4-9B. We identify model dependent interaction horizons (15 to 30 turns) and decompose outcomes into overall success rate (SR), safe success rate (SSR), and unsafe success rate (USR). Our results reveal a persistent Safety Capability Gap. While safety mediation can intercept up to 94 percent of non-compliant actions, it rarely translates into strictly safe goal attainment (SSR below 5 percent in most settings). We find that high unsafe success rates are primarily driven by Integrity Leaks, where models hallucinate user identifiers to bypass mandatory authentication. Recovery rates following blocked actions are consistently low, ranging from 21 percent for GPT-OSS-20B in simpler procedural tasks to near zero in complex Retail scenarios. These results demonstrate that runtime enforcement imposes a significant verifier tax on conversational length and compute cost without guaranteeing safe completion, highlighting the critical need for agents capable of grounded identity verification and post-intervention reasoning.

LLM agents have demonstrated remarkable performance across various applications, primarily due to their advanced capabilities in reasoning, utilizing external knowledge and tools, calling APIs, and executing actions to interact with environments. Current agents typically utilize a memory module or a retrieval-augmented generation (RAG) mechanism, retrieving past knowledge and instances with similar embeddings from knowledge bases to inform task planning and execution. However, the reliance on unverified knowledge bases raises significant concerns about their safety and trustworthiness. To uncover such vulnerabilities, we propose a novel red teaming approach AgentPoison, the first backdoor attack targeting generic and RAG-based LLM agents by poisoning their long-term memory or RAG knowledge base. In particular, we form the trigger generation process as a constrained optimization to optimize backdoor triggers by mapping the triggered instances to a unique embedding space, so as to ensure that whenever a user instruction contains the optimized backdoor trigger, the malicious demonstrations are retrieved from the poisoned memory or knowledge base with high probability. In the meantime, benign instructions without the trigger will still maintain normal performance. Unlike conventional backdoor attacks, AgentPoison requires no additional model training or fine-tuning, and the optimized backdoor trigger exhibits superior transferability, in-context coherence, and stealthiness. Extensive experiments demonstrate AgentPoison's effectiveness in attacking three types of real-world LLM agents: RAG-based autonomous driving agent, knowledge-intensive QA agent, and healthcare EHRAgent. On each agent, AgentPoison achieves an average attack success rate higher than 80% with minimal impact on benign performance (less than 1%) with a poison rate less than 0.1%.

Indirect prompt injection poses a critical threat to LLM agents that interact with untrusted external data, yet automated attack methods--proven effective for jailbreaking--remain underexplored in realistic agentic settings. We present a comprehensive empirical evaluation of automated prompt injection attacks against LLM agents, adapting both white-box (GCG) and black-box (TAP) methods to the agentic setting within the AgentDojo framework. We evaluate across 80 task pairs spanning four domains and multiple models, and find that black-box optimization substantially outperforms gradient-based methods, a gap we attribute to GCG's optimization instability under reasonable compute budgets. We also find that TAP's effectiveness depends on the attacker model, as both general capability and safety tuning affect attack success--stronger models produce more effective injections, while safety-tuned attackers can refuse to generate adversarial prompts. Task-universal attacks transfer effectively to unseen tasks and out-of-distribution domains, but attacks optimized on smaller open-source models do not transfer to frontier models like GPT-5. These findings highlight automated prompt injection as a credible but model-dependent threat, with significant barriers remaining for model-agnostic exploitation.

LLM as judge systems used to assess text quality code correctness and argument strength are vulnerable to prompt injection attacks. We introduce a framework that separates content author attacks from system prompt attacks and evaluate five models Gemma 3.27B Gemma 3.4B Llama 3.2 3B GPT 4 and Claude 3 Opus on four tasks with various defenses using fifty prompts per condition. Attacks achieved up to seventy three point eight percent success smaller models proved more vulnerable and transferability ranged from fifty point five to sixty two point six percent. Our results contrast with Universal Prompt Injection and AdvPrompter We recommend multi model committees and comparative scoring and release all code and datasets

This paper provides a systematic analysis of the opportunities, challenges, and potential solutions of harnessing Large Language Models (LLMs) such as GPT-4 to dig out vulnerabilities within smart contracts based on our ongoing research. For the task of smart contract vulnerability detection, achieving practical usability hinges on identifying as many true vulnerabilities as possible while minimizing the number of false positives. Nonetheless, our empirical study reveals contradictory yet interesting findings: generating more answers with higher randomness largely boosts the likelihood of producing a correct answer but inevitably leads to a higher number of false positives. To mitigate this tension, we propose an adversarial framework dubbed GPTLens that breaks the conventional one-stage detection into two synergistic stages - generation and discrimination, for progressive detection and refinement, wherein the LLM plays dual roles, i.e., auditor and critic, respectively. The goal of auditor is to yield a broad spectrum of vulnerabilities with the hope of encompassing the correct answer, whereas the goal of critic that evaluates the validity of identified vulnerabilities is to minimize the number of false positives. Experimental results and illustrative examples demonstrate that auditor and critic work together harmoniously to yield pronounced improvements over the conventional one-stage detection. GPTLens is intuitive, strategic, and entirely LLM-driven without relying on specialist expertise in smart contracts, showcasing its methodical generality and potential to detect a broad spectrum of vulnerabilities. Our code is available at: https://github.com/git-disl/GPTLens.

Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluations are conducted by designing inputs that elicit harmful behaviors from the system. However, a fundamental limitation of this approach is that the harmfulness of the behaviors identified during any particular evaluation can only lower bound the model's worst-possible-case behavior. As a complementary method for eliciting harmful behaviors, we propose evaluating LLMs with model tampering attacks which allow for modifications to latent activations or weights. We pit state-of-the-art techniques for removing harmful LLM capabilities against a suite of 5 input-space and 6 model tampering attacks. In addition to benchmarking these methods against each other, we show that (1) model resilience to capability elicitation attacks lies on a low-dimensional robustness subspace; (2) the attack success rate of model tampering attacks can empirically predict and offer conservative estimates for the success of held-out input-space attacks; and (3) state-of-the-art unlearning methods can easily be undone within 16 steps of fine-tuning. Together these results highlight the difficulty of removing harmful LLM capabilities and show that model tampering attacks enable substantially more rigorous evaluations than input-space attacks alone. We release models at https://huggingface.co/LLM-GAT

As LLM-based agents increasingly browse the web on users' behalf, a natural question arises: can websites passively identify which underlying model powers an agent? Doing so would represent a significant security risk, enabling targeted attacks tailored to known model vulnerabilities. Across 14 frontier LLMs and four web environments spanning information retrieval and shopping tasks, we show that an agent's actions and interaction timings, captured via a passive JavaScript tracker, are sufficient to identify the underlying model with up to 96\% F1. We formalise this attack surface by demonstrating that classifiers trained on agent actions generalise across model sizes and families. We further show that strong classifiers can be trained from few interaction traces and that agent identity can be inferred early within an episode. Injecting randomised timing delays between actions substantially degrades classifier performance, but does not provide robust protection: a classifier retrained on delayed traces largely recovers performance. We release our harness and a labelled corpus of agent traces https://github.com/KabakaWilliam/known_actions{here}.

Retrieval-augmented generation (RAG) is increasingly deployed in real-world applications, where its reference-grounded design makes outputs appear trustworthy. This trust has spurred research on poisoning attacks that craft malicious content, inject it into knowledge sources, and manipulate RAG responses. However, when evaluated in practical RAG systems, existing attacks suffer from severely degraded effectiveness. This gap stems from two overlooked realities: (i) content is often processed before use, which can fragment the poison and weaken its effect, and (ii) users often do not issue the exact queries anticipated during attack design. These factors can lead practitioners to underestimate risks and develop a false sense of security. To better characterize the threat to practical systems, we present Confundo, a learning-to-poison framework that fine-tunes a large language model as a poison generator to achieve high effectiveness, robustness, and stealthiness. Confundo provides a unified framework supporting multiple attack objectives, demonstrated by manipulating factual correctness, inducing biased opinions, and triggering hallucinations. By addressing these overlooked challenges, Confundo consistently outperforms a wide range of purpose-built attacks across datasets and RAG configurations by large margins, even in the presence of defenses. Beyond exposing vulnerabilities, we also present a defensive use case that protects web content from unauthorized incorporation into RAG systems via scraping, with no impact on user experience.

Most studies of prompt injection focus on generative agents, leaving their effects on models with schema-defined outputs unclear. We examine these effects in Jev, a non-generative decision model, using 510 reconstructed InjecAgent cases. Malicious content shifts action probabilities but rarely causes Jev to select the attacker's target. Override markers reduce this influence, while claims of contextual relatedness have small effects. Adaptive attacks using score feedback double the mean highest attacker-target probability found during optimization, while success on fresh validation calls rises from 1.8% to 3.5%. Exploratory analysis links these successes to small initial decision margins or greater attacker control over the observation. Together, these findings show that schema-defined outputs change but do not eliminate prompt-injection risk, highlighting the need to evaluate how untrusted content influences choices within the allowed action set.

Large language model (LLM) agents combine language-based reasoning with external tools to perform complex tasks. Adversarial inputs can exploit interactions between the agent and its environment, causing the agent to violate safety policies during execution. Yet existing evaluations often reduce agent safety to a single attack success rate (ASR), collapsing exposure, execution, observation, and adjudication and potentially conflating actual violations with evidence visibility. We introduce REDAgentBench, an executable framework for autonomous red-teaming and faithful measurement. It derives attacks from explicit safety constraints and associated agent-system vulnerabilities, runs them in isolated service sandboxes, and verifies harmful effects from service receipts and final-state changes. The benchmark contains 1,661 cases across five service surfaces. Across six models and three agent harnesses, macro-average ASR is 65.69%; reported ASR varies with harness and evidence view, while evaluation-context disclosure changes execution behavior. In a state-grounded diagnostic cohort, almost one in five confirmed violations with resolved action anchors occurs after the agent states the relevant constraint or risk, revealing a Recognition--Execution Gap. Finally, a training-free policy reminder reduces confirmed violations by more than 70 percentage points in matched replay. These findings show that executable evaluation can improve safety measurement and identify actionable intervention points.

We systematically evaluate the quality of widely used AI safety datasets from two perspectives: in isolation and in practice. In isolation, we examine how well these datasets reflect real-world adversarial attacks based on three key properties: being driven by ulterior intent, well-crafted, and out-of-distribution. We find that these datasets overrely on "triggering cues": words or phrases with overt negative/sensitive connotations that are intended to trigger safety mechanisms explicitly, which is unrealistic compared to real-world attacks. In practice, we evaluate whether these datasets genuinely measure safety risks or merely provoke refusals through triggering cues. To explore this, we introduce "intent laundering": a procedure that abstracts away triggering cues from adversarial attacks (data points) while strictly preserving their malicious intent and all relevant details. Our results indicate that current AI safety datasets fail to faithfully represent real-world adversarial behavior due to their overreliance on triggering cues. Once these cues are removed, all previously evaluated "reasonably safe" models become unsafe, including Gemini 3 Pro and Claude Sonnet 3.7. Moreover, when intent laundering is adapted as a jailbreaking technique, it consistently achieves high attack success rates, ranging from 90% to over 98%, under fully black-box access. Overall, our findings expose a significant disconnect between how model safety is evaluated by existing datasets and how real-world adversaries behave.

Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a wide variety of 'jailbreaking' techniques to elicit harmful text from models that were fine-tuned to be harmless. Recent work on red-teaming, model editing, and interpretability suggests that this challenge stems from how (adversarial) fine-tuning largely serves to suppress rather than remove undesirable capabilities from LLMs. Prior work has introduced latent adversarial training (LAT) as a way to improve robustness to broad classes of failures. These prior works have considered untargeted latent space attacks where the adversary perturbs latent activations to maximize loss on examples of desirable behavior. Untargeted LAT can provide a generic type of robustness but does not leverage information about specific failure modes. Here, we experiment with targeted LAT where the adversary seeks to minimize loss on a specific competing task. We find that it can augment a wide variety of state-of-the-art methods. First, we use targeted LAT to improve robustness to jailbreaks, outperforming a strong R2D2 baseline with orders of magnitude less compute. Second, we use it to more effectively remove backdoors with no knowledge of the trigger. Finally, we use it to more effectively unlearn knowledge for specific undesirable tasks in a way that is also more robust to re-learning. Overall, our results suggest that targeted LAT can be an effective tool for defending against harmful behaviors from LLMs.

Large language models (LLMs) are typically aligned to be harmless to humans. Unfortunately, recent work has shown that such models are susceptible to automated jailbreak attacks that induce them to generate harmful content. More recent LLMs often incorporate an additional layer of defense, a Guard Model, which is a second LLM that is designed to check and moderate the output response of the primary LLM. Our key contribution is to show a novel attack strategy, PRP, that is successful against several open-source (e.g., Llama 2) and closed-source (e.g., GPT 3.5) implementations of Guard Models. PRP leverages a two step prefix-based attack that operates by (a) constructing a universal adversarial prefix for the Guard Model, and (b) propagating this prefix to the response. We find that this procedure is effective across multiple threat models, including ones in which the adversary has no access to the Guard Model at all. Our work suggests that further advances are required on defenses and Guard Models before they can be considered effective.

LLM agents choose tools and arguments from context that mixes user requests, tool outputs, retrieved records, memory, and untrusted text. Evidence can be relevant without being authorized to determine a decision, so a correct action need not be grounded only in permitted evidence. We introduce a target-specific authorization audit that labels context factors separately for each tool and argument target. Its primary test holds the task, proposition, position, and policy fixed while changing only the proposition's source authority. We then test behavior when valid evidence is weakened and use context-subset interactions as a secondary localization diagnostic. Across 450 controlled next-action tasks and multiple open-weight LLM families, trusted and untrusted variants produce different actions in 5.4 percent of competing cases versus 1.7 percent of supporting cases. Under controlled degradation, unauthorized competition is retained in a full-correct, mixed-error, clean-correct pattern in 2.4 percent of comparisons, with a 95 percent confidence interval from 2.1 to 3.0 percent. These are controlled stress-set rates, not deployment prevalence. The models respond to textual source-authority cues, but this does not prevent untrusted evidence from influencing their actions.

The security of Large Language Model (LLM) applications is fundamentally challenged by "form-first" attacks like prompt injection and jailbreaking, where malicious instructions are embedded within user inputs. Conventional defenses, which rely on post hoc output filtering, are often brittle and fail to address the root cause: the model's inability to distinguish trusted instructions from untrusted data. This paper proposes Countermind, a multi-layered security architecture intended to shift defenses from a reactive, post hoc posture to a proactive, pre-inference, and intra-inference enforcement model. The architecture proposes a fortified perimeter designed to structurally validate and transform all inputs, and an internal governance mechanism intended to constrain the model's semantic processing pathways before an output is generated. The primary contributions of this work are conceptual designs for: (1) A Semantic Boundary Logic (SBL) with a mandatory, time-coupled Text Crypter intended to reduce the plaintext prompt injection attack surface, provided all ingestion paths are enforced. (2) A Parameter-Space Restriction (PSR) mechanism, leveraging principles from representation engineering, to dynamically control the LLM's access to internal semantic clusters, with the goal of mitigating semantic drift and dangerous emergent behaviors. (3) A Secure, Self-Regulating Core that uses an OODA loop and a learning security module to adapt its defenses based on an immutable audit log. (4) A Multimodal Input Sandbox and Context-Defense mechanisms to address threats from non-textual data and long-term semantic poisoning. This paper outlines an evaluation plan designed to quantify the proposed architecture's effectiveness in reducing the Attack Success Rate (ASR) for form-first attacks and to measure its potential latency overhead.

Large Language Models (LLMs) are increasingly used in a variety of important applications, yet their safety and reliability remain as major concerns. Various adversarial and jailbreak attacks have been proposed to bypass the safety alignment and cause the model to produce harmful responses. We introduce Self-supervised Prompt INjection (SPIN) which can detect and reverse these various attacks on LLMs. As our self-supervised prompt defense is done at inference-time, it is also compatible with existing alignment and adds an additional layer of safety for defense. Our benchmarks demonstrate that our system can reduce the attack success rate by up to 87.9%, while maintaining the performance on benign user requests. In addition, we discuss the situation of an adaptive attacker and show that our method is still resilient against attackers who are aware of our defense.

The model context protocol (MCP) has been widely adapted as an open standard enabling the seamless integration of generative AI agents. However, recent work has shown the MCP is susceptible to retrieval-based "falsely benign" attacks (FBAs), allowing malicious system access and credential theft, but requiring that users download compromised files directly to their systems. Herein, we show that the threat model of MCP-based attacks is significantly broader than previously thought, i.e., attackers need only post malicious content online to deceive MCP agents into carrying out their attacks on unsuspecting victims' systems. To improve alignment guardrails against such attacks, we introduce a new MCP dataset of FBAs and (truly) benign samples to explore the effectiveness of direct preference optimization (DPO) for the refusal training of large language models (LLMs). While DPO improves model guardrails against such attacks, we show that the efficacy of refusal learning varies drastically depending on the model's original post-training alignment scheme--e.g., GRPO-based LLMs learn to refuse extremely poorly. Thus, to further improve FBA refusals, we introduce Retrieval Augmented Generation for Preference alignment (RAG-Pref), a novel preference alignment strategy based on RAG. We show that RAG-Pref significantly improves the ability of LLMs to refuse FBAs, particularly when combined with DPO alignment, thus drastically improving guardrails against MCP-based attacks.

Agent skills occupy a privileged position in the agent workflow, as agents are expected to implicitly follow and execute them, rendering third-party skills a vulnerable attack surface. Existing studies have revealed unsafe agent behaviors induced by skill-based attacks, but they primarily evaluate poisoned skills within a single task execution and enumerate harms through ad-hoc risk lists. To bridge these gaps, we introduce SkillHarm, a benchmark of skill-based attacks across the skill-use lifecycle, paired with a systematic taxonomy of skill-relevant risks. SkillHarm evaluates two attack scenarios: Fixed-Payload Poisoning (FPP), where a fixed poisoned skill package directly compromises any task session that invokes it, and Self-Mutating Poisoning (SMP), where an initially benign execution silently mutates persistent skill content, deferring harm until a subsequent reuse. It further defines 12 risk types based on the agent workflow component targeted by the harm: data pipelines, system environments, and agent autonomy. To instantiate these attacks at scale, we build AutoSkillHarm, an automated construction pipeline with coding agents driven by natural-language harnesses. The resulting benchmark contains 879 attack samples across 71 skills. Experiments show that current agents remain vulnerable with attack success rates up to 86.3% in FPP and 69.3% in SMP. Our analysis further reveals a latent risk: many apparent attack failures stem from the agent failing to engage with the poisoned file rather than genuine resistance, and current defenses still fail to reliably mitigate the threat.

Safeguards in deployed LLM services are evaluated by refusal, attack success, and policy violation rates. Those rates characterize how a control performed on the requests it was tested on. A deployment has to answer a different question: how much help with harmful tasks the service still gives an attacker who keeps adapting or finds another way in. We determine what each reported result implies for that question, allowing results from different safeguard families to be compared under one deployment criterion. The evidence requirements are strongly asymmetric. One attack that obtains harmful help from the deployed service suffices to establish that such help remains, and such attacks appear repeatedly in the coded record. Establishing that little remains cannot follow from the safeguard's own numbers alone; it also requires evidence about what the surrounding system still allows after the safeguard performs its local function. Such evidence is supported or derived in only a small minority of the depth-coded claims, and one such claim bounds its scoped residual. A better local score is therefore not, by itself, a stronger claim about the deployment. Safeguard research cannot stop at raising local scores; a gain has to be judged by whether it makes a deployed system any safer.

Deterministic pre-execution safety gates evaluate whether individual agent actions are compatible with their assigned roles. While effective at per-action authorization, these systems are structurally blind to distributed attacks that decompose harmful intent across multiple individually-compliant steps. This paper introduces Session Risk Memory (SRM), a lightweight deterministic module that extends stateless execution gates with trajectory-level authorization. SRM maintains a compact semantic centroid representing the evolving behavioral profile of an agent session and accumulates a risk signal through exponential moving average over baseline-subtracted gate outputs. It operates on the same semantic vector representation as the underlying gate, requiring no additional model components, training, or probabilistic inference. We evaluate SRM on a multi-turn benchmark of 80 sessions containing slow-burn exfiltration, gradual privilege escalation, and compliance drift scenarios. Results show that ILION+SRM achieves F1 = 1.0000 with 0% false positive rate, compared to stateless ILION at F1 = 0.9756 with 5% FPR, while maintaining 100% detection rate for both systems. Critically, SRM eliminates all false positives with a per-turn overhead under 250 microseconds. The framework introduces a conceptual distinction between spatial authorization consistency (evaluated per action) and temporal authorization consistency (evaluated over trajectory), providing a principled basis for session-level safety in agentic systems.

It has been shown that Large Language Model (LLM) alignments can be circumvented by appending specially crafted attack suffixes with harmful queries to elicit harmful responses. To conduct attacks against private target models whose characterization is unknown, public models can be used as proxies to fashion the attack, with successful attacks being transferred from public proxies to private target models. The success rate of attack depends on how closely the proxy model approximates the private model. We hypothesize that for attacks to be transferrable, it is sufficient if the proxy can approximate the target model in the neighborhood of the harmful query. Therefore, in this paper, we propose Local Fine-Tuning (LoFT), i.e., fine-tuning proxy models on similar queries that lie in the lexico-semantic neighborhood of harmful queries to decrease the divergence between the proxy and target models. First, we demonstrate three approaches to prompt private target models to obtain similar queries given harmful queries. Next, we obtain data for local fine-tuning by eliciting responses from target models for the generated similar queries. Then, we optimize attack suffixes to generate attack prompts and evaluate the impact of our local fine-tuning on the attack's success rate. Experiments show that local fine-tuning of proxy models improves attack transferability and increases attack success rate by 39%, 7%, and 0.5% (absolute) on target models ChatGPT, GPT-4, and Claude respectively.

Prompt leakage poses a compelling security and privacy threat in LLM applications. Leakage of system prompts may compromise intellectual property, and act as adversarial reconnaissance for an attacker. A systematic evaluation of prompt leakage threats and mitigation strategies is lacking, especially for multi-turn LLM interactions. In this paper, we systematically investigate LLM vulnerabilities against prompt leakage for 10 closed- and open-source LLMs, across four domains. We design a unique threat model which leverages the LLM sycophancy effect and elevates the average attack success rate (ASR) from 17.7% to 86.2% in a multi-turn setting. Our standardized setup further allows dissecting leakage of specific prompt contents such as task instructions and knowledge documents. We measure the mitigation effect of 7 black-box defense strategies, along with finetuning an open-source model to defend against leakage attempts. We present different combination of defenses against our threat model, including a cost analysis. Our study highlights key takeaways for building secure LLM applications and provides directions for research in multi-turn LLM interactions

This study systematically analyzes the vulnerability of 36 large language models (LLMs) to various prompt injection attacks, a technique that leverages carefully crafted prompts to elicit malicious LLM behavior. Across 144 prompt injection tests, we observed a strong correlation between model parameters and vulnerability, with statistical analyses, such as logistic regression and random forest feature analysis, indicating that parameter size and architecture significantly influence susceptibility. Results revealed that 56 percent of tests led to successful prompt injections, emphasizing widespread vulnerability across various parameter sizes, with clustering analysis identifying distinct vulnerability profiles associated with specific model configurations. Additionally, our analysis uncovered correlations between certain prompt injection techniques, suggesting potential overlaps in vulnerabilities. These findings underscore the urgent need for robust, multi-layered defenses in LLMs deployed across critical infrastructure and sensitive industries. Successful prompt injection attacks could result in severe consequences, including data breaches, unauthorized access, or misinformation. Future research should explore multilingual and multi-step defenses alongside adaptive mitigation strategies to strengthen LLM security in diverse, real-world environments.

Although promising, existing defenses against query-based attacks share a common limitation: they offer increased robustness against attacks at the price of a considerable accuracy drop on clean samples. In this work, we show how to efficiently establish, at test-time, a solid tradeoff between robustness and accuracy when mitigating query-based attacks. Given that these attacks necessarily explore low-confidence regions, our insight is that activating dedicated defenses, such as random noise defense and random image transformations, only for low-confidence inputs is sufficient to prevent them. Our approach is independent of training and supported by theory. We verify the effectiveness of our approach for various existing defenses by conducting extensive experiments on CIFAR-10, CIFAR-100, and ImageNet. Our results confirm that our proposal can indeed enhance these defenses by providing better tradeoffs between robustness and accuracy when compared to state-of-the-art approaches while being completely training-free.

We show that LoRA adapters, the dominant distribution format for fine-tuned LLMs, can be reliably backdoored through training data poisoning while preserving baseline task performance. On a Qwen 2.5 1.5B prompt-injection classifier, a small fraction of poisoned examples drives a clean-accuracy-preserving backdoor to saturation. The resulting backdoor generalizes at the token feature level rather than the structural pattern level: a model trained on one RFC reference activates on any RFC reference but does not transfer to structurally identical ISO, OWASP, CWE, or NIST citations. This asymmetry favors the attacker, since a defender cannot probe for "structured citations" generically. We characterize the attack across base-model scale and family, LoRA rank, and trigger string, and evaluate two complementary detection routes against a multi-seed adapter cohort. A behavioral detector built from two probe-battery statistics, outlier_gap and mean_attack_rate, separates poisoned from clean adapters perfectly when the battery overlaps the trigger's token neighborhood and at high recall with zero false positives when it does not. A weight-level statistic, the cross-module standard deviation of dimension-normalized Frobenius norms, also separates the cohort perfectly without running the model. Combined, the two routes are robust to probe composition. Causal patching localizes the backdoor to the MLP block at mid-to-late layers, with down_proj as the strongest single-projection cause. Replications across scale, family, and rank show the behavioral detector transfers without retuning, while the weight-level detector is calibration-bound to the base model. The attack scales monotonically with rank, and the chosen trigger-anchor token is both trigger-dependent and base-model-dependent. Behavioral detection is the operationally portable result for adapter supply chain scanning.

While the deployment of large language models (LLMs) in high-value industries continues to expand, the systematic assessment of their safety against jailbreak and prompt-based attacks remains insufficient. Existing safety evaluation benchmarks and frameworks are often limited by an imbalanced integration of core components (attack, defense, and evaluation methods) and an isolation between flexible evaluation frameworks and standardized benchmarking capabilities. These limitations hinder reliable cross-study comparisons and create unnecessary overhead for comprehensive risk assessment. To address these gaps, we present TeleAI-Safety, a modular and reproducible framework coupled with a systematic benchmark for rigorous LLM safety evaluation. Our framework integrates a broad collection of 19 attack methods (including one self-developed method), 29 defense methods, and 19 evaluation methods (including one self-developed method). With a curated attack corpus of 342 samples spanning 12 distinct risk categories, the TeleAI-Safety benchmark conducts extensive evaluations across 14 target models. The results reveal systematic vulnerabilities and model-specific failure cases, highlighting critical trade-offs between safety and utility, and identifying potential defense patterns for future optimization. In practical scenarios, TeleAI-Safety can be flexibly adjusted with customized attack, defense, and evaluation combinations to meet specific demands. We release our complete code and evaluation results to facilitate reproducible research and establish unified safety baselines.

LLM-based agents process external content, exposing them to prompt injection and multi-turn manipulation. Most safety benchmarks evaluate defenders against fixed attack pools collected before evaluation, single-turn or multi-turn. We present a 21-scenario benchmark for adaptive multi-round attacks against memoryless LLM defenders: an autonomous LLM attacker observes prior defender responses and pivots across rounds, while each defender response is evaluated as a fresh interaction. Holding the 21 scenarios, attackers, defenders, and structured-output scoring fixed, restricting scoring to the first attacker turn yields 0-1% attack success rate (ASR); allowing 15 rounds of adaptive attack yields 5.4-14.0%. Pooling three frontier attacker LLMs uncovers 1.4-2.2times as many unique successful attacks as the best single attacker, and the generated attacks have low cosine similarity (0.02-0.14) to attacks in existing benchmarks. Claude Opus 4.6 and GPT-5.4 are tied in aggregate (5.4% each; overlapping 95% CIs), but their weaknesses differ sharply: on one scenario Opus reaches 60% ASR (95% CI 36--80%) while GPT-5.4 and Gemini each stay at 7% (CI 1-30%; the gap is preserved in a higher-N replication). 13 of 21 scenarios distinguish at least one defender pair, yet rankings disagree across scenarios (Kendall's W = 0.19). We release the benchmark -- 21 evaluation scenarios, 10 public development scenarios, the orchestrator, baseline harnesses, and a multi-attacker CLI -- plus 945 transcripts from the 3times3 frontier matrix, an attack-replay dataset, and 18{,}422 gpt-oss-20b battles from an open competition's final scoring rounds.

Foundation models are increasingly becoming better autonomous programmers, raising the prospect that they could also automate dangerous offensive cyber-operations. Current frontier model audits probe the cybersecurity risks of such agents, but most fail to account for the degrees of freedom available to adversaries in the real world. In particular, with strong verifiers and financial incentives, agents for offensive cybersecurity are amenable to iterative improvement by would-be adversaries. We argue that assessments should take into account an expanded threat model in the context of cybersecurity, emphasizing the varying degrees of freedom that an adversary may possess in stateful and non-stateful environments within a fixed compute budget. We show that even with a relatively small compute budget (8 H100 GPU Hours in our study), adversaries can improve an agent's cybersecurity capability on InterCode CTF by more than 40\% relative to the baseline -- without any external assistance. These results highlight the need to evaluate agents' cybersecurity risk in a dynamic manner, painting a more representative picture of risk.

The widespread deployment of Large Language Models (LLMs) as public-facing web services and APIs has made their security a core concern for the web ecosystem. Jailbreak attacks, as one of the significant threats to LLMs, have recently attracted extensive research. In this paper, we reveal a jailbreak strategy which can effectively evade current defense strategies. It can extract valuable information from failed or partially successful attack attempts and contains self-evolution from attack interactions, resulting in sufficient strategy diversity and adaptability. Inspired by continuous learning and modular design principles, we propose ASTRA, a jailbreak framework that autonomously discovers, retrieves, and evolves attack strategies to achieve more efficient and adaptive attacks. To enable this autonomous evolution, we design a closed-loop "attack-evaluate-distill-reuse" core mechanism that not only generates attack prompts but also automatically distills and generalizes reusable attack strategies from every interaction. To systematically accumulate and apply this attack knowledge, we introduce a three-tier strategy library that categorizes strategies into Effective, Promising, and Ineffective based on their performance scores. The strategy library not only provides precise guidance for attack generation but also possesses exceptional extensibility and transferability. We conduct extensive experiments under a black-box setting, and the results show that ASTRA achieves an average Attack Success Rate (ASR) of 82.7%, significantly outperforming baselines.

As generative AI, particularly large language models (LLMs), become increasingly integrated into production applications, new attack surfaces and vulnerabilities emerge and put a focus on adversarial threats in natural language and multi-modal systems. Red-teaming has gained importance in proactively identifying weaknesses in these systems, while blue-teaming works to protect against such adversarial attacks. Despite growing academic interest in adversarial risks for generative AI, there is limited guidance tailored for practitioners to assess and mitigate these challenges in real-world environments. To address this, our contributions include: (1) a practical examination of red- and blue-teaming strategies for securing generative AI, (2) identification of key challenges and open questions in defense development and evaluation, and (3) the Attack Atlas, an intuitive framework that brings a practical approach to analyzing single-turn input attacks, placing it at the forefront for practitioners. This work aims to bridge the gap between academic insights and practical security measures for the protection of generative AI systems.

The integration of large language models with external content has enabled applications such as Microsoft Copilot but also introduced vulnerabilities to indirect prompt injection attacks. In these attacks, malicious instructions embedded within external content can manipulate LLM outputs, causing deviations from user expectations. To address this critical yet under-explored issue, we introduce the first benchmark for indirect prompt injection attacks, named BIPIA, to assess the risk of such vulnerabilities. Using BIPIA, we evaluate existing LLMs and find them universally vulnerable. Our analysis identifies two key factors contributing to their success: LLMs' inability to distinguish between informational context and actionable instructions, and their lack of awareness in avoiding the execution of instructions within external content. Based on these findings, we propose two novel defense mechanisms-boundary awareness and explicit reminder-to address these vulnerabilities in both black-box and white-box settings. Extensive experiments demonstrate that our black-box defense provides substantial mitigation, while our white-box defense reduces the attack success rate to near-zero levels, all while preserving the output quality of LLMs. We hope this work inspires further research into securing LLM applications and fostering their safe and reliable use.