Illustration drawn by RepoMasters from the repo’s ID and its language color. Credits
PrototypeCommon

leigest519/HiddenDetect

ACL 2025 (Main) HiddenDetect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden States

Owner
leigest519 (personal account)
Stars
Stars: 167
Forks
Forks: 3
Language
Python
License
None
Created
2025
Tier
Prototype (100 to 249 ★) What this tier means
View on GitHub

More repos by leigest519

All 3 repos by leigest519

Nearby in Python

All Python repos