A Hamiltonian Monte Carlo Method for Probabilistic Adversarial Attack and Learning

Although deep convolutional neural networks (CNNs) have demonstrated remarkable performance on multiple computer vision tasks, researches on adversarial learning have shown that deep models are vulnerable to adversarial examples, which are crafted by adding visually imperceptible perturbations to th...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 4 vom: 28. Apr., Seite 1725-1737
1. Verfasser:	Wang, Hongjun (VerfasserIn)
Weitere Verfasser:	Li, Guanbin, Liu, Xiaobai, Lin, Liang
Format:	Online-Aufsatz
Sprache:	English
Veröffentlicht:	2022
Zugriff auf das übergeordnete Werk:	IEEE transactions on pattern analysis and machine intelligence
Schlagworte:	Journal Article Research Support, Non-U.S. Gov't