Toward Understanding and Boosting Adversarial Transferability From a Distribution Perspective

Transferable adversarial attacks against Deep neural networks (DNNs) have received broad attention in recent years. An adversarial example can be crafted by a surrogate model and then attack the unknown target model successfully, which brings a severe threat to DNNs. The exact underlying reasons for...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on image processing 2022, Vol.31, p.6487-6501
Hauptverfasser:	Zhu, Yao, Chen, Yuefeng, Li, Xiaodan, Chen, Kejiang, He, Yuan, Tian, Xiang, Zheng, Bolun, Chen, Yaowu, Huang, Qingming
Format:	Artikel
Sprache:	eng
Schlagworte:	adversarial attack Adversarial transferability Artificial neural networks black-box attack Data models Distributed databases Image classification Image enhancement Image manipulation Iterative methods Neural networks Perturbation methods Predictive models Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!