Pinned

1. tml-epfl/llm-adaptive-attacks tml-epfl/llm-adaptive-attacks Public

   Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]

   Shell 108 8

2. JailbreakBench/jailbreakbench JailbreakBench/jailbreakbench Public

   An Open Robustness Benchmark for Jailbreaking Language Models [arXiv 2024]

   Python 88 11

3. RobustBench/robustbench RobustBench/robustbench Public

   RobustBench: a standardized adversarial robustness benchmark [NeurIPS'21 Benchmarks and Datasets Track]

   Python 608 95

4. tml-epfl/understanding-fast-adv-training tml-epfl/understanding-fast-adv-training Public

   Understanding and Improving Fast Adversarial Training [NeurIPS 2020]

   Python 91 12

5. square-attack square-attack Public

   Square Attack: a query-efficient black-box adversarial attack via random search [ECCV 2020]

   Python 144 26

6. relu_networks_overconfident relu_networks_overconfident Public

   Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem [CVPR 2019, oral]

   Python 182 21