Texture Re-Scalable Universal Adversarial Perturbation

Universal adversarial perturbation (UAP), also known as image-agnostic perturbation, is a fixed perturbation map that can fool the classifier with high probabilities on arbitrary images, making it more practical for attacking deep models in the real world. Previous UAP methods generate a scale-fixed...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on information forensics and security 2024, Vol.19, p.8291-8305
Hauptverfasser:	Huang, Yihao, Guo, Qing, Juefei-Xu, Felix, Hu, Ming, Jia, Xiaojun, Cao, Xiaochun, Pu, Geguang, Liu, Yang
Format:	Artikel
Sprache:	eng
Schlagworte:	Adversarial attack Generative adversarial networks Noise Optimization Perturbation methods texture scale Training Training data universal adversarial perturbation Vectors
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!