Rethinking Backdoor Detection Evaluation for Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yan, Jun, Mo, Wenjie Jacky, Ren, Xiang, Jia, Robin
Format:	Preprint
Published:	2024
Subjects:	Computation and Language 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/2409.00399