Forbidden Question Dataset

The dataset used to evaluate the effectiveness of different jailbreak attack methods against LLMs. The dataset contains 160 forbidden questions with high diversity.

Data and Resources

Cite this as

Junjie Chu, Yugeng Liu, Ziqing Yang, Xinyue Shen, Michael Backes, Yang Zhang (2024). Dataset: Forbidden Question Dataset. https://doi.org/10.57702/17h8ml2l

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Junjie Chu
More Authors
Yugeng Liu
Ziqing Yang
Xinyue Shen
Michael Backes
Yang Zhang