Augment then Smooth: Reconciling Differential Privacy with Certified Robustness

Machine learning models are susceptible to a variety of attacks that can erode trust, including attacks against the privacy of training data, and adversarial examples that jeopardize model accuracy. Differential privacy and certified robustness are effective frameworks for combating these two threat...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Wu, Jiapeng, Ghomi, Atiyeh Ashari, Glukhov, David, Cresswell, Jesse C, Boenisch, Franziska, Papernot, Nicolas
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Cryptography and Security Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!