Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Zongru, Zhang, Zhuosheng, Cheng, Pengzhou, Liu, Gongshen
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence 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/2402.12026