Federated Learning With Differential Privacy: Algorithms and Performance Analysis

Federated learning (FL), as a type of distributed machine learning, is capable of significantly preserving clients’ private data from being exposed to adversaries. Nevertheless, private information can still be divulged by analyzing uploaded parameters from clients, e.g., weights trained in deep neural networks. In this paper, to effectively prevent information leakage, we propose a novel framework based on the concept of differential privacy (DP), in which artificial noise is added to parameters at the clients’ side before aggregating, namely, noising before model aggregation FL (NbAFL). First, we prove that the NbAFL can satisfy DP under distinct protection levels by properly adapting different variances of…

• NS
  National Science Foundation

  Award: CCF-1908308
• NN
  National Natural Science Foundation of China

  Awards: 61872184, 61727802
• NK
  National Key Research and Development Program of China

  Award: 2018YFB1004800