UW-NSL

Pinned Loading

1. SafeDecoding SafeDecoding Public

   Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding

   Jupyter Notebook 152 17

2. ArtPrompt ArtPrompt Public

   [ACL24] Official Repo of Paper `ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs`

   Python 100 21

3. ChatBug ChatBug Public

   [AAAI25] Official Repo of Paper `ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates`

   Python 14 1

4. CleanGen CleanGen Public

   [EMNLP 24] Official Implementation of CLEANGEN: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models

   Python 19 2

5. safechain safechain Public

   [ACL 25] SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities

   Python 30 3

6. TinyV TinyV Public

   Your efficient and accurate answer verification system for RL training.

   Python 41 2