Safety Layers in Aligned Large Language Models: The Key to LLM Security

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Shen, Yao, Liuyi, Zhang, Lan, Li, Yaliang
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/2408.17003