Erosion Attack : Harnessing Corruption To Improve Adversarial Examples

Although adversarial examples pose a serious threat to deep neural networks, most transferable adversarial attacks are ineffective against black-box defense models. This may lead to the mistaken belief that adversarial examples are not truly threatening. In this paper, we propose a novel transferabl...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 32(2023) vom: 25., Seite 4828-4841
1. Verfasser: Huang, Lifeng (VerfasserIn)
Weitere Verfasser: Gao, Chengying, Liu, Ning
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2023
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article