Jailbreak Attacks Analysis Transformer Models

There are 6 jailbreak attacks analysis models tracked. The highest-rated is UCSB-NLP-Chang/SemanticSmooth at 30/100 with 23 stars.

Get all 6 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
1 UCSB-NLP-Chang/SemanticSmooth

Implementation of paper 'Defending Large Language Models against Jailbreak...

30
Emerging
2 sigeisler/reinforce-attacks-llms

REINFORCE Adversarial Attacks on Large Language Models: An Adaptive,...

29
Experimental
3 DAMO-NLP-SG/multilingual-safety-for-LLMs

[ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"

27
Experimental
4 yueliu1999/FlipAttack

[ICML 2025] An official source code for paper "FlipAttack: Jailbreak LLMs...

25
Experimental
5 wanglne/DELMAN

[ACL 2025 Findings] DELMAN: Dynamic Defense Against Large Language Model...

16
Experimental
6 itsvaibhav01/Immune

[CVPR2025] Official Repository for IMMUNE: Improving Safety Against...

14
Experimental