Backdoor Attack With Sparse and Invisible Trigger

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where the adversary manipulates a small portion of training data such that the victim model predicts normally on the benign samples but classifies the triggered samples as the target class. The backdoor attack is an emerging yet threate...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on information forensics and security 2024, Vol.19, p.6364-6376
Hauptverfasser:	Gao, Yinghua, Li, Yiming, Gong, Xueluan, Li, Zhifeng, Xia, Shu-Tao, Wang, Qian
Format:	Artikel
Sprache:	eng
Schlagworte:	Additives AI security Artificial neural networks Backdoor attack Data models invisibility Optimization Perturbation methods Security sparsity Task analysis Training trustworthy ML
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!