Generalization Techniques Empirically Outperform Differential Privacy against Membership Inference

Differentially private training algorithms provide protection against one of the most popular attacks in machine learning: the membership inference attack. However, these privacy algorithms incur a loss of the model's classification accuracy, therefore creating a privacy-utility trade-off. The...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2021-10
Hauptverfasser:	Liu, Jiaxiang, Simon, Oya, Kerschbaum, Florian
Format:	Artikel
Sprache:	eng
Schlagworte:	Acceptable noise levels Algorithms Deep learning Inference Machine learning Model accuracy Noise levels Privacy Sharpness
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!