Boosting Accuracy of Differentially Private Continuous Data Release for Federated Learning

Incorporating differentially private continuous data release (DPCR) into private federated learning (FL) has recently emerged as a powerful technique for enhancing accuracy. Designing an effective DPCR model is the key to improving accuracy. Still, the state-of-the-art DPCR models hinder the potenti...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on information forensics and security 2024, Vol.19, p.10287-10301
Hauptverfasser:	Cai, Jianping, Ye, Qingqing, Hu, Haibo, Liu, Ximeng, Fu, Yanggeng
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy binary indexed tree continuous data release Data models differential privacy Estimation Federated learning Matrix decomposition matrix mechanism Noise Parametric statistics Privacy Resource management Vectors
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!