Jailbreak Attacks Analysis LLM Tools

Tools, datasets, and methods for generating, analyzing, and understanding jailbreak attacks against LLMs—including attack taxonomies, prompt injection techniques, and adversarial methods. Does NOT include defense mechanisms, safety alignment, or general robustness improvements.

There are 16 jailbreak attacks analysis tools tracked. 2 score above 50 (established tier). The highest-rated is wuyoscar/ISC-Bench at 68/100 with 677 stars. 2 of the top 10 are actively maintained.

Get all 16 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=llm-tools&subcategory=jailbreak-attacks-analysis&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Tool	Score	Tier	Stars	Language
1	wuyoscar/ISC-Bench Internal Safety Collapse: Turning LLMs into a "Jailbroken State" Without "a...	68	Established	677	Python
2	yueliu1999/Awesome-Jailbreak-on-LLMs Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel,...	57	Established	1,245	—
3	yiksiu-chan/SpeakEasy [ICML 2025] Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple...	42	Emerging	14	Python
4	xirui-li/DrAttack Official implementation of paper: DrAttack: Prompt Decomposition and...	35	Emerging	66	JavaScript
5	Techiral/awesome-llm-jailbreaks Latest AI Jailbreak Payloads & Exploit Techniques for GPT, QWEN, and all LLM Models	34	Emerging	60	—
6	tmlr-group/DeepInception [arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"	34	Emerging	172	Python
7	NeuralTrust/echo-chamber Code and examples for Echo Chamber LLM Jailbreak.	32	Emerging	5	Jupyter Notebook
8	CryptoAILab/FigStep [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic...	31	Emerging	193	Python
9	erfanshayegani/Jailbreak-In-Pieces [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak...	26	Experimental	80	Python
10	AetherPrior/TrickLLM This repository contains the code for the paper "Tricking LLMs into...	26	Experimental	8	Jupyter Notebook
11	RobustNLP/DeRTa A novel approach to improve the safety of large language models, enabling...	24	Experimental	72	Python
12	vicgalle/merging-self-critique-jailbreaks "Merging Improves Self-Critique Against Jailbreak Attacks", code and models	22	Experimental	1	Jupyter Notebook
13	michael-borck/taxonomy-of-ai-jailbreaks Categorizes AI jailbreak tactics using taxonomic analysis to enhance LLM...	21	Experimental	2	HTML
14	Yahy5715/jailbreak-defense Detect and prevent large language model jailbreaks using hidden state causal...	14	Experimental	—	—
15	Glor1us/llm-jailbreak-vulnerability-analysis Experimental study of jailbreak and prompt injection vulnerabilities in...	14	Experimental	—	Jupyter Notebook
16	KDEGroup/MPA Source code for COLING'25 paper "Monte Carlo Tree Search Based Prompt...	13	Experimental	7	Shell

Comparisons in this category

Awesome-Jailbreak-on-LLMs and awesome-llm-jailbreaks (57 vs 34)