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.
This resource provides a curated collection of techniques for evaluating and improving the safety of Large Language Models (LLMs). It includes research papers, code, and datasets related to both 'jailbreak' attacks (attempts to bypass safety mechanisms) and defenses against them. AI safety researchers and practitioners who are building or deploying LLMs would use this to understand vulnerabilities and develop more robust, responsible AI systems.
1,245 stars. Actively maintained with 14 commits in the last 30 days.
Use this if you are a researcher or engineer focused on understanding, testing, and hardening the safety mechanisms of Large Language Models against adversarial exploits.
Not ideal if you are looking for a plug-and-play tool for general LLM development or for simple prompt engineering.
Stars
1,245
Forks
101
Language
—
License
MIT
Category
Last pushed
Mar 07, 2026
Commits (30d)
14
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/yueliu1999/Awesome-Jailbreak-on-LLMs"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
wuyoscar/ISC-Bench
Internal Safety Collapse: Turning LLMs into a "Jailbroken State" Without "a Jailbreak Attack".
yiksiu-chan/SpeakEasy
[ICML 2025] Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
xirui-li/DrAttack
Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes...
tmlr-group/DeepInception
[arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"
Techiral/awesome-llm-jailbreaks
Latest AI Jailbreak Payloads & Exploit Techniques for GPT, QWEN, and all LLM Models