Scalable Multi-Round Multi-Party Privacy-Preserving Neural Network Training

Privacy-preserving machine learning has achieved breakthrough advances in collaborative training of machine learning models, under strong information-theoretic privacy guarantees. Despite the recent advances, communication bottleneck still remains as a major challenge against scalability in neural n...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on information theory 2024-11, Vol.70 (11), p.8204-8236
Hauptverfasser:	Lu, Xingyu, Basaran, Umit Yigit, Guler, Basak
Format:	Artikel
Sprache:	eng
Schlagworte:	collaborative training Complexity theory Computational modeling Encoding information-theoretic privacy Machine learning Privacy Privacy-preserving machine learning Resilience Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!