Smoothed Inference for Adversarially-Trained Models

Deep neural networks are known to be vulnerable to adversarial attacks. Current methods of defense from such attacks are based on either implicit or explicit regularization, e.g., adversarial training. Randomized smoothing, the averaging of the classifier outputs over a random distribution centered...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Nemcovsky, Yaniv, Zheltonozhskii, Evgenii, Baskin, Chaim, Chmiel, Brian, Fishman, Maxim, Bronstein, Alex M, Mendelson, Avi
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning Statistics - Machine Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!