A comprehensive collection of cutting-edge jailbreak methods, datasets, codes, and analyses targeting large language models (LLMs).
Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, datasets, evaluations, and analyses.
This repository serves researchers and security analysts aiming to study, evaluate, and develop jailbreak attacks and defenses on LLMs. It provides curated resources including papers, datasets, and code implementations to facilitate understanding and experimentation with LLM vulnerabilities and safeguards.
This repository is primarily a curated dataset and resource collection rather than a standalone tool with installable commands; users should refer to linked papers and code repositories for implementation details. It is intended for academic and research purposes, requiring familiarity with LLM security concepts.