Classifiers Protected against Attacks by Fusion of Multi-Branch Perturbed GAN

Deep learning is widely used in classification tasks to achieve advanced performance. However, in the face of well-designed image classifications, such as the Fast Gradient Sign Method (FGSM), there are glaring errors. This paper proposes a new technique to eliminate interference using generative ad...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Mobile networks and applications 2020-12, Vol.25 (6), p.2321-2335
Hauptverfasser:	Hu, Jianjun, Yu, Mengjing, Xu, Qingzhen, Gao, Jing
Format:	Artikel
Sprache:	eng
Schlagworte:	Classification Communications Engineering Computer Communication Networks Electrical Engineering Engineering Generative adversarial networks Image classification Interference IT in Business Machine learning Networks Perturbation Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!