Popular repositories Loading

1. JBShield JBShield Public

   Code for USENIX Security 2025 paper "JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation"

   Python 177 22

2. AT-BSL AT-BSL Public

   Code for CVPR 2024 "Revisiting Adversarial Training under Long-Tailed Distributions".

   Python 158 94

3. CleanSheet CleanSheet Public

   Code and full version of the paper "Hijacking Attacks against Neural Network by Analyzing Training Data"

   Python 12 4

4. LVID_Dataset LVID_Dataset Public