An Optimized Sparse Response Mechanism for Differentially Private Federated Learning

• Published in: IEEE transactions on dependable and secure computing Vol. 21; no. 4; pp. 2285 - 2295
• Main Authors: Ma, Jiating, Zhou, Yipeng, Cui, Laizhong, Guo, Song
• Format: Journal Article
• Language: English
• Published: Washington IEEE 01.07.2024; IEEE Computer Society
• Subjects: Algorithms; Budgets; Clients; Computational modeling; Convergence; convergence rate; Data models; Differential privacy; differentially private; Distortion; Exposure; Federated learning; Parameters; Privacy; sparse response; Training

Federated Learning (FL) enables geo-distributed clients to collaboratively train a learning model without exposing their private data. By only exposing local model parameters, FL well preserves data privacy of clients. Yet, it remains possible to recover raw samples from over frequently exposed para...