Utilizing Adversarial Targeted Attacks to Boost Adversarial Robustness

Adversarial attacks have been shown to be highly effective at degrading the performance of deep neural networks (DNNs). The most prominent defense is adversarial training, a method for learning a robust model. Nevertheless, adversarial training does not make DNNs immune to adversarial perturbations....

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Pesso, Uriya, Bibas, Koby, Feder, Meir
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computer Vision and Pattern Recognition
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!