PinnedLoading

1. Awesome-LM-SSPAwesome-LM-SSPPublic

   A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

   1.3k 83

2. misalignmentmisalignmentPublic

   [NDSS'25] The official implementation of safety misalignment.

   Python 7 1

3. FigStepFigStepPublic

   [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts

   Python 121 6

4. MergeGuardMergeGuardPublic

   [CCS-LAMPS'24] LLM IP Protection Against Model Merging

   Python 13 1

5. JailbreakEvalJailbreakEvalPublic

   [NDSS'25 Poster] A collection of automated evaluators for assessing jailbreak attempts.

   Python 127 10