Pinned Loading

1. AutoDAN AutoDAN Public

   [ICLR 2024] The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models".

   Python 401 54

2. SaFoLab-WISC/AutoDAN-Turbo SaFoLab-WISC/AutoDAN-Turbo Public

   [ICLR 2025 Spotlight] The official implementation of our ICLR2025 paper "AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs".

   Python 325 52

3. Universal-Prompt-Injection Universal-Prompt-Injection Public

   The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".

   Python 64 8

4. CGCL-codes/TeCo CGCL-codes/TeCo Public

   [CVPR 2023] The official implementation of our CVPR 2023 paper "Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency".

   Python 23 3

5. CGCL-codes/AMT-GAN CGCL-codes/AMT-GAN Public

   [CVPR 2022] The official implementation of our CVPR 2022 paper "Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfer".

   Python 91 14