Pinned Loading

1. Awesome-LM-SSP Awesome-LM-SSP Public

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

   2k 150

2. misalignment misalignment Public

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

   Python 19 1

3. FigStep FigStep Public

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

   Python 209 13

4. CryptoBackdoor CryptoBackdoor Public

   [KDD'26] Rethinking the Stealthiness of Cryptographically Undetectable Backdoors in Practical RFF Learning

   Python

5. GhostVAE GhostVAE Public

   [USENIX Security'26] Robust Watermarks Meet Backdoored Models: Evading Diffusion Semantic Watermarks via Stealthy Backdoor

   Python

6. FakeI2V-Bench FakeI2V-Bench Public

   [KDD D&B Track 2026] FakeI2V-Bench: Benchmarking the Applicability of Image-level Deepfake Detectors for Deepfake Video Detection

   Jupyter Notebook