BadTemplate: A Training-Free Backdoor Attack via Chat Template Against Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Zihan, Li, Hongwei, Zhang, Rui, Jiang, Wenbo, Xu, Guowen
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2602.05401