M-to-N Backdoor Paradigm: A Multi-Trigger and Multi-Target Attack to Deep Learning Models

journal contribution

posted on 2025-05-05, 06:57 authored by Linshan Hou, Zhongyun Hua, Yuhong Li, Yifeng Zheng, Leo ZhangLeo Zhang

M-to-N Backdoor Paradigm: A Multi-Trigger and Multi-Target Attack to Deep Learning Models

History

Journal

IEEE Transactions on Circuits and Systems for Video Technology

Volume

34

Pagination

11299-11312

Location

Piscataway, N.J.

Open access

No

ISSN

1051-8215

eISSN

1558-2205

Language

eng

Publication classification

C1.1 Refereed article in a scholarly journal

Issue

11

Publisher

IEEE

Publication URL

http://dx.doi.org/10.1109/tcsvt.2024.3417410

Usage metrics

Categories

Keywords

backdoor attack clean features deep neural networks poisoning attach trojan attack

Licence

All Rights Reserved

Exports