Pinned Loading

1. Code for the paper "Defeating Prompt Injections by Design"

   Jupyter Notebook 371 57

2. A research workbench for developing and testing attacks against large language models, with a focus on prompt injection vulnerabilities and defenses.

   Python 61 21

3. A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.

   Python 756 195

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

   Python 781 106

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

   Python 654 76

6. Code used to run the platform for the LLM CTF colocated with SaTML 2024

   Python 29 6