A dataset of jailbreak-related prompts for ChatGPT, aiding in understanding and generating text in this context.
Dataset for classifying prompts as jailbreak or benign to enhance LLM safety.
A collection of state-of-the-art jailbreak methods for LLMs, including papers, codes, datasets, and analyses.
A powerful tool for automated LLM fuzzing to identify and mitigate potential jailbreaks in LLM APIs.
A dataset of 15,140 ChatGPT prompts, including 1,405 jailbreak prompts, collected from various platforms for research purposes.
