-
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... -
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. -
Jailbreak Attack Dataset
The dataset used in the paper to evaluate the effectiveness of different jailbreak attack methods against Large Language Models (LLMs).
