Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

Deep neural networks are proven to be vulnerable to backdoor attacks. Detecting the trigger samples during the inference stage, i.e., the test-time trigger sample detection, can prevent the backdoor from being triggered. However, existing detection methods often require the defenders to have high ac...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-03
Hauptverfasser:	Liu, Xiaogeng, Li, Minghui, Wang, Haoyu, Hu, Shengshan, Ye, Dengpan, Jin, Hai, Wu, Libing, Xiao, Chaowei
Format:	Artikel
Sprache:	eng
Schlagworte:	Accessibility Artificial neural networks Consistency Inference Robustness Testing time
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!