Principal Component Adversarial Example

Despite having achieved excellent performance on various tasks, deep neural networks have been shown to be susceptible to adversarial examples, i.e., visual inputs crafted with structural imperceptible noise. To explain this phenomenon, previous works implicate the weak capability of the classificat...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - (2020) vom: 28. Feb.
1. Verfasser:	Zhang, Yonggang (VerfasserIn)
Weitere Verfasser:	Tian, Xinmei, Li, Ya, Wang, Xinchao, Tao, Dacheng
Format:	Online-Aufsatz
Sprache:	English
Veröffentlicht:	2020
Zugriff auf das übergeordnete Werk:	IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:	Journal Article