You're currently viewing an old version of this dataset. To see the current version, click here.

Jailbreak Prompts and Malicious Queries

The dataset comprises 448 in-the-wild jailbreak prompts and 161 malicious queries, with which the authors derived a systemization of five categories and ten unique jailbreak patterns.

Data and Resources

Cite this as

Zhiyuan Yu, Xiaogeng Liu, Shunning Liang, Zach Cameron, Chaowei Xiao, Ning Zhang (2024). Dataset: Jailbreak Prompts and Malicious Queries. https://doi.org/10.57702/oflrezk1

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.2403.17336
Author Zhiyuan Yu
More Authors
Xiaogeng Liu
Shunning Liang
Zach Cameron
Chaowei Xiao
Ning Zhang
Homepage https://llmjailbreak.github.io/