AdvBench

The dataset used in the paper to test the Gradient Cuff method for detecting jailbreak attacks on large language models.

Data and Resources

Cite this as

Xiaomeng Hu, Pin-Yu Chen, Tsung-Yi Ho (2024). Dataset: AdvBench. https://doi.org/10.57702/iqh9imd4

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2402.05723
Citation
  • https://doi.org/10.48550/arXiv.2403.00867
  • https://doi.org/10.48550/arXiv.2405.20778
Author Xiaomeng Hu
More Authors
Pin-Yu Chen
Tsung-Yi Ho
Homepage https://huggingface.co/datasets/llm-attacks