RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Miao, Yu, Feng, Ning, Rui, Li, Lusi, Chen, Jiawei, Lou, Qian, Zheng, Mengxin, Xin, Chunsheng, Wu, Hongyi
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2602.00183