Adversarially Robust Neural Architectures

Deep Neural Networks (DNNs) are vulnerable to adversarial attacks. Existing methods are devoted to developing various robust training strategies or regularizations to update the weights of the neural network. But beyond the weights, the overall structure and information flow in the network are expli...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 47(2025), 5 vom: 04. Mai, Seite 4183-4197
1. Verfasser: Dong, Minjing (VerfasserIn)
Weitere Verfasser: Li, Yanxi, Wang, Yunhe, Xu, Chang
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2025
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article