Awesome-Jailbreak-on-LLMs and awesome-llm-jailbreaks
These are complements that serve different purposes: one is an academic/research repository cataloging jailbreak methodologies with papers and analyses, while the other is a practical payload collection for testing and exploitation, used together to understand jailbreaks both theoretically and operationally.
About Awesome-Jailbreak-on-LLMs
yueliu1999/Awesome-Jailbreak-on-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.
Organizes attack and defense methods across multiple threat vectors—targeting reasoning models, black-box/white-box scenarios, multi-turn conversations, RAG systems, and multi-modal inputs—alongside guardrail approaches like learning-based defenses and guard models. The repository indexes implementation code and datasets alongside paper citations, enabling reproducible comparison of attack/defense effectiveness. Covers emerging safety challenges in reasoning-heavy LLMs (o1-style models) and multimodal systems alongside traditional text-based jailbreaks.
About awesome-llm-jailbreaks
Techiral/awesome-llm-jailbreaks
Latest AI Jailbreak Payloads & Exploit Techniques for GPT, QWEN, and all LLM Models
Scores updated daily from GitHub, PyPI, and npm data. How scores work