JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Shenyi, Zhai, Yuchen, Guo, Keyan, Hu, Hongxin, Guo, Shengnan, Fang, Zheng, Zhao, Lingchen, Shen, Chao, Wang, Cong, Wang, Qian
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.07557