ZeroGrad : Mitigating and Explaining Catastrophic Overfitting in FGSM Adversarial Training

Making deep neural networks robust to small adversarial noises has recently been sought in many applications. Adversarial training through iterative projected gradient descent (PGD) has been established as one of the mainstream ideas to achieve this goal. However, PGD is computationally demanding an...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2021-03
Hauptverfasser:	Golgooni, Zeinab, Saberi, Mehrdad, Masih Eskandar, Mohammad Hossein Rohban
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Artificial neural networks Datasets Iterative methods Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!