Security-gUided Reasoning and learnIng

university

https://henrygwb.github.io/lab.htm

https://github.com/ucsb-mlsec

AI & ML interests

Code LLMs, AI agents for security, Reasoning

authored a paper 8 months ago

TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents

Paper • 2602.07274 • Published Feb 6 • 42

submitted a paper to Daily Papers 9 months ago

TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents

Paper • 2602.07274 • Published Feb 6 • 42

updated a model 9 months ago

UCSB-SURFI/TermiGen-32B

Text Generation • 1.12M • Updated Feb 10 • 37 • 4

updated a collection 11 months ago

VulnLLM-R

Data and model for VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection • 9 items • Updated Dec 17, 2025 • 9

authored a paper over 1 year ago

Progent: Programmable Privilege Control for LLM Agents

Paper • 2504.11703 • Published Apr 16, 2025 • 6

authored 5 papers over 2 years ago

PromptBench: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts

Paper • 2306.04528 • Published Jun 7, 2023 • 3

A Survey on Evaluation of Large Language Models

Paper • 2307.03109 • Published Jul 6, 2023 • 41

Improving Generalization of Adversarial Training via Robust Critical Fine-Tuning

Paper • 2308.02533 • Published Aug 1, 2023

Large Language Models Understand and Can be Enhanced by Emotional Stimuli

Paper • 2307.11760 • Published Jul 14, 2023 • 1

DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks

Paper • 2309.17167 • Published Sep 29, 2023 • 1

authored a paper almost 3 years ago

PromptBench: A Unified Library for Evaluation of Large Language Models

Paper • 2312.07910 • Published Dec 13, 2023 • 16