Structure Estimation of Adversarial Distributions for Enhancing Model Robustness: A Clustering-Based Approach

In this paper, we propose an advanced method for adversarial training that focuses on leveraging the underlying structure of adversarial perturbation distributions. Unlike conventional adversarial training techniques that consider adversarial examples in isolation, our approach employs clustering al...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Bader Rasheed, Adil Khan, Asad Masood Khattak
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	MDPI AG 2023-10-01
Schriftenreihe:	Applied Sciences
Schlagworte:	deep neural networks robustness adversarial attacks adversarial training clustering
Online-Zugang:	https://www.mdpi.com/2076-3417/13/19/10972
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!