Defusing the Trigger: Plug-and-Play Defense for Backdoored LLMs via Tail-Risk Intrinsic Geometric Smoothing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fan, Kaisheng, Zhang, Weizhe, Gao, Yishu, Bissyandé, Tegawendé F., Tang, Xunzhu
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/2604.24162