FLoomChecker: Repelling Free-riders in Federated Learning via Training Integrity Verification

Federated learning is a mechanism that allows participating clients to train locally with their own data in order to receive rewards, thus avoiding the transfer of data to a central server and protecting users' privacy. However, some "lazy" clients may adopt the strategy of fabricatin...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Proceedings - International Conference on Parallel and Distributed Systems S. 194 - 201
Hauptverfasser:	Liang, Guanghao, Chang, Shan, Dai, Minghui, Zhu, Hongzi
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 10.10.2024
Schlagworte:	Bloom filter Computational modeling Data models Data privacy Federated learning Filters Free-rider attack Servers TEE Training Training data Training integrity verification
ISSN:	2690-5965
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!