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

NISPLab/JBShield

Code for USENIX Security 2025 paper "JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation"

Owner
NISPLab (personal account)
Stars
Stars: 226
Forks
Forks: 29
Language
Python
License
MIT
Created
2025
Tier
Prototype (100 to 249 ★) What this tier means
View on GitHub

More repos by NISPLab

All 2 repos by NISPLab

Nearby in Python

All Python repos