User-Level Label Leakage from Gradients in Federated Learning

Federated learning enables multiple users to build a joint model by sharing their model updates (gradients), while their raw data remains local on their devices. In contrast to the common belief that this provides privacy benefits, we here add to the very recent results on privacy risks when sharing...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Proceedings on Privacy Enhancing Technologies 2022-04, Vol.2022 (2), p.227-244
Hauptverfasser:	Wainakh, Aidmar, Ventola, Fabrizio, Müßig, Till, Keim, Jens, Cordero, Carlos Garcia, Zimmer, Ephraim, Grube, Tim, Kersting, Kristian, Mühlhäuser, Max
Format:	Artikel
Sprache:	eng
Schlagworte:	federated learning gradient attack Label leakage privacy attack
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!