Probing the Safety Response Boundary of Large Language Models via Unsafe Decoding Path Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Haoyu, Wu, Bingzhe, Bian, Yatao, Chang, Yongzhe, Wang, Xueqian, Zhao, Peilin
Format:	Preprint
Published:	2024
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/2408.10668