Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks

Deep neural networks are vulnerable to adversarial examples, which can mislead classifiers by adding imperceptible perturbations. An intriguing property of adversarial examples is their good transferability, making black-box attacks feasible in real-world applications. Due to the threat of adversari...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) S. 4307 - 4316
Hauptverfasser:	Dong, Yinpeng, Pang, Tianyu, Su, Hang, Zhu, Jun
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 01.06.2019
Schlagworte:	Categorization Codes Computational modeling Computer vision Deep learning Glass box Kernel Pattern recognition Perturbation methods Recognition: Detection Retrieval Robustness Security
ISSN:	1063-6919
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!