PyRIT icon indicating copy to clipboard operation
PyRIT copied to clipboard

FEAT Add JailbreakV_28K dataset

Open chenss3 opened this issue 6 months ago • 0 comments

Is your feature request related to a problem? Please describe.

Add this dataset into PyRIT - it is not currently apart of PyRIT yet. https://huggingface.co/datasets/JailbreakV-28K/JailBreakV-28k/viewer/JailBreakV_28K/mini_JailBreakV_28K?views%5B%5D=jailbreakv_28k_mini_jailbreakv_28k&row=4

Describe the solution you'd like

The HuggingFace data set: https://huggingface.co/datasets/JailbreakV-28K/JailBreakV-28k/viewer/JailBreakV_28K/mini_JailBreakV_28K?views%5B%5D=jailbreakv_28k_mini_jailbreakv_28k&row=4 The associated paper: https://arxiv.org/abs/2404.03027

Additional context

Similar to previous dataset contributions this should live in pyrit.datasets as a "fetch" function. Also, the harm_categories property should be set on each prompt. This huggingface dataset mentions each harm category under the "policy" column. There are examples of how PyRIT interacts with other datasets here: https://github.com/search?q=repo%3AAzure%2FPyRIT%20%23%20The%20dataset%20sources%20can%20be%20found%20at%3A&type=code

[[Content Warning: Prompts are aimed at provoking the model, and may contain offensive content.]] Additional Disclaimer: Given the content of these prompts, keep in mind that you may want to check with your relevant legal department before trying them against LLMs.

chenss3 avatar Jul 16 '25 21:07 chenss3