2 datasets found

Tags: AdvBench

Filter Results

  • AdvBench dataset

    The dataset used for the experiments in the paper, consisting of 60 harmful instructions from the AdvBench dataset.

  • AdvBench

    The dataset used in the paper to test the Gradient Cuff method for detecting jailbreak attacks on large language models.
You can also access this registry using the API (see API Docs).