Defending against high-poisoning backdoor attacks by exploiting loss divergence
Information Fusion · 2026-09 · 133 · 104308
DOI: 10.1016/j.inffus.2026.104308 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information Fusion, 2026-09. Verfasst von Yuzhuo Jin und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: Science and Technology Department of Sichuan Province, National Natural Science Foundation of China.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- Science and Technology Department of Sichuan Province
- National Natural Science Foundation of China
Zitieren
APA
Jin, Y., Wang, R., Wang, N., He, D., Zhang, Y., & Liu, Z. (2026). Defending against high-poisoning backdoor attacks by exploiting loss divergence. Information Fusion, 133, 104308. https://doi.org/10.1016/j.inffus.2026.104308
Vancouver
Jin Y, Wang R, Wang N, He D, Zhang Y, Liu Z. Defending against high-poisoning backdoor attacks by exploiting loss divergence. Information Fusion. 2026;133:104308. doi:10.1016/j.inffus.2026.104308
BibTeX
@article{Jin2026,
author = {Jin, Yuzhuo and Wang, Ruijin and Wang, Na and He, Donglin and Zhang, Yang and Liu, Zhiquan},
title = {Defending against high-poisoning backdoor attacks by exploiting loss divergence},
journal = {Information Fusion},
year = {2026},
volume = {133},
pages = {104308},
doi = {10.1016/j.inffus.2026.104308}
}
EUVIMED