Depth Charge: Jailbreak Large Language Models from Deep Safety Attention Heads

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Jinman, Xie, Yi, Zhao, Shiqian, Chen, Xiaofeng
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.05772