Exploiting the Vulnerability of Large Language Models via Defense-Aware Architectural Backdoor

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Miah, Abdullah Arafat, Bi, Yu
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Artificial Intelligence Hardware Architecture
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2409.01952