FedAdOb: Privacy-Preserving Federated Deep Learning with Adaptive Obfuscation

Federated learning (FL) has emerged as a collaborative approach that allows multiple clients to jointly learn a machine learning model without sharing their private data. The concern about privacy leakage, albeit demonstrated under specific conditions, has triggered numerous follow-up research in de...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-06
Hauptverfasser:	Gu, Hanlin, Luo, Jiahuan, Kang, Yan, Yao, Yuan, Zhu, Gongxi, Bowen, Li, Fan, Lixin, Yang, Qiang
Format:	Artikel
Sprache:	eng
Schlagworte:	Deep learning Federated learning Machine learning Privacy
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!