You Can't Fool All the Models: Detect Adversarial Samples via Pruning Models

Many adversarial attack methods have investigated the security issue of deep learning models. Previous works on detecting adversarial samples show superior in accuracy but consume too much memory and computing resources. In this paper, we propose an adversarial sample detection method based on prune...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE access 2021, Vol.9, p.163780-163790
Hauptverfasser:	Wang, Renxuan, Chen, Zuohui, Dong, Hui, Xuan, Qi
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Adaptation models Adversarial sample detection adversarial defense adversarial attack DNN model pruning Computational modeling Data models Machine learning Neural networks Perturbation methods Pruning Robustness Testing Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!