Jailbreak Attacks Analysis Transformer Models

There are 9 jailbreak attacks analysis models tracked. The highest-rated is UCSB-NLP-Chang/SemanticSmooth at 37/100 with 23 stars.

Get all 9 projects as JSON

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

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

#	Model	Score	Tier	Stars	Language
1	UCSB-NLP-Chang/SemanticSmooth Implementation of paper 'Defending Large Language Models against Jailbreak...	37	Emerging	23	Python
2	sigeisler/reinforce-attacks-llms REINFORCE Adversarial Attacks on Large Language Models: An Adaptive,...	36	Emerging	23	Python
3	DAMO-NLP-SG/multilingual-safety-for-LLMs [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"	34	Emerging	101	—
4	yueliu1999/FlipAttack [ICML 2025] An official source code for paper "FlipAttack: Jailbreak LLMs...	32	Emerging	167	Python
5	vicgalle/merging-self-critique-jailbreaks "Merging Improves Self-Critique Against Jailbreak Attacks", code and models	29	Experimental	1	Jupyter Notebook
6	wanglne/DELMAN [ACL 2025 Findings] DELMAN: Dynamic Defense Against Large Language Model...	22	Experimental	9	Python
7	itsvaibhav01/Immune [CVPR2025] Official Repository for IMMUNE: Improving Safety Against...	21	Experimental	27	Python
8	Yahy5715/jailbreak-defense Detect and prevent large language model jailbreaks using hidden state causal...	14	Experimental	—	—
9	Glor1us/llm-jailbreak-vulnerability-analysis Experimental study of jailbreak and prompt injection vulnerabilities in...	13	Experimental	—	Jupyter Notebook