Pinned Loading

1. tml-epfl/os-harm tml-epfl/os-harm Public

   OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents [NeurIPS 2025 Spotlight]

   Jupyter Notebook 40

2. tml-epfl/llm-past-tense tml-epfl/llm-past-tense Public

   Does Refusal Training in LLMs Generalize to the Past Tense? [ICLR 2025]

   Python 77 11

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

   Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]

   Shell 365 39

4. JailbreakBench/jailbreakbench JailbreakBench/jailbreakbench Public

   JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]

   Python 469 52

5. tml-epfl/why-weight-decay tml-epfl/why-weight-decay Public

   Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]

   Python 69 2

6. RobustBench/robustbench RobustBench/robustbench Public

   RobustBench: a standardized adversarial robustness benchmark [NeurIPS 2021 Benchmarks and Datasets Track]

   Python 753 100