Adversarial training in logit space against tiny perturbations

Adversarial training is wildly considered as one of the most effective ways to defend against adversarial examples. However, existing adversarial training methods consume unbearable time, due to the fact that they need to generate adversarial examples in a large input space. To speed up adversarial...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Multimedia systems 2023-12, Vol.29 (6), p.3277-3290
Hauptverfasser:	Guan, Xiaohui, Shao, Qiqi, Qian, Yaguan, Yao, Tengteng, Wang, Bin
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Communication Networks Computer Graphics Computer Science Cryptology Data Storage Representation Multimedia Information Systems Operating Systems Perturbation Regular Paper Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!