Layer-wise Regularized Adversarial Training using Layers Sustainability Analysis (LSA) framework

Deep neural network models are used today in various applications of artificial intelligence, the strengthening of which, in the face of adversarial attacks is of particular importance. An appropriate solution to adversarial attacks is adversarial training, which reaches a trade-off between robustne...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-02
Hauptverfasser:	Khalooei, Mohammad, Homayounpour, Mohammad Mehdi, Amirmazlaghani, Maryam
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial intelligence Artificial neural networks Benchmarks Computer architecture Error analysis Multilayer perceptrons Neural networks Perturbation Regularization Sustainability Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!