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

Hou, Linshan; Hua, Zhongyun; Li, Yuhong; Zheng, Yifeng; Zhang, Leo

File(s) not publicly available

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

journal contribution

posted on 2024-08-05, 22:19 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

PP

Location

Piscataway, N.J.

Publisher DOI

https://doi.org/10.1109/tcsvt.2024.3417410

ISSN

1051-8215

eISSN

1558-2205

Language

en

Publication classification

C1.1 Refereed article in a scholarly journal

Issue

99

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Usage metrics

Keywords

backdoor attack poisoning attach trojan attack clean features deep neural networks

Licence

Exports

RefWorks

BibTeX

Ref. manager

Endnote

DataCite

NLM

DC

File(s) not publicly available

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

History

Journal

Volume

Location

Publisher DOI

ISSN

eISSN

Language

Publication classification

Issue

Publisher

Usage metrics

Categories

Keywords

Licence

Exports