AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Zijun, Tu, Haoqin, Mei, Jieru, Zhao, Bingchen, Wang, Yisen, Xie, Cihang
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2410.09040