Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation

Adversarial Training (AT) has been widely proved to be an effective method to improve the adversarial robustness against adversarial examples for Deep Neural Networks (DNNs). As a variant of AT, Adversarial Robustness Distillation (ARD) has demonstrated its superior performance in improving the robu...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-10
Hauptverfasser:	Zhao, Shiji, Duan, Ranjie, Wang, Xizhe, Wei, Xingxing
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Bias Distillation Empirical analysis Error analysis Labels Robustness Smoothness Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!