Privacy-Preserving Deep Learning via Additively Homomorphic Encryption

We present a privacy-preserving deep learning system in which many learning participants perform neural network-based deep learning over a combined dataset of all, without revealing the participants' local data to a central server. To that end, we revisit the previous work by Shokri and Shmatik...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on information forensics and security 2018-05, Vol.13 (5), p.1333-1345
Hauptverfasser:	Le Trieu Phong, Aono, Yoshinori, Hayashi, Takuya, Lihua Wang, Moriai, Shiho
Format:	Artikel
Sprache:	eng
Schlagworte:	additively homomorphic encryption deep learning Encryption LWE-based encryption Machine learning neural network Neural networks Paillier encryption Privacy Servers
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!