Backdoor Samples Detection Based on Perturbation Discrepancy Consistency in Pre-trained Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Peng, Zuquan, Fu, Jianming, Zou, Lixin, Zheng, Li, Ren, Yanzhen, Peng, Guojun
Format:	Preprint
Published:	2025
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/2509.05318