Joaquín Herrera

joaco-h

6 9

·

AI & ML interests

AI alignment, jailbreak detection, red teaming, model robustness, safety evaluation

Recent Activity

upvoted a paper about 12 hours ago

Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models

liked a dataset 4 days ago

walledai/JailbreakHub

liked a dataset 4 days ago

Cleanlab/FinQA-hallucination-detection

View all activity

Organizations

None yet

liked 3 datasets 4 days ago

walledai/JailbreakHub

Viewer • Updated Jul 31, 2024 • 15.1k • 4.38k • 32

Cleanlab/FinQA-hallucination-detection

Viewer • Updated Mar 3, 2025 • 1.66k • 1.01k • 3

JailbreakV-28K/JailBreakV-28k

Viewer • Updated Jul 10, 2024 • 30.3k • 11.9k • 74

liked a model 4 days ago

nvidia/NemoGuard-JailbreakDetect

Updated Apr 2 • 282 • 30

liked 2 models 5 days ago

Alignment-Lab-AI/OpenVoice

Text-to-Speech • Updated Jan 5, 2024 • 12

SamsungSDS-Research/SGuard-JailbreakFilter-2B-v1

Text Generation • 3B • Updated Dec 15, 2025 • 545 • 20

liked a model 7 days ago

Alignment-Lab-AI/Mistral-Large-Instruct-Q3XS-llamafile

Updated Aug 1, 2024 • 7 • 5

liked 2 datasets 8 days ago

Mindgard/evaded-prompt-injection-and-jailbreak-samples

Viewer • Updated Apr 30, 2025 • 11.3k • 191 • 21

rubend18/ChatGPT-Jailbreak-Prompts

Viewer • Updated Aug 24, 2023 • 79 • 13.6k • 278