DeepAI AI Chat
Log In Sign Up

Federated Learning with Differential Privacy: Algorithms and Performance Analysis

by   Kang Wei, et al.

In this paper, to effectively prevent information leakage, we propose a novel framework based on the concept of differential privacy (DP), in which artificial noises are added to the 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 artificial noises. Then we develop a theoretical convergence bound of the loss function of the trained FL model in the NbAFL. Specifically, the theoretical bound reveals the following three key properties: 1) There is a tradeoff between the convergence performance and privacy protection levels, i.e., a better convergence performance leads to a lower protection level; 2) Given a fixed privacy protection level, increasing the number N of overall clients participating in FL can improve the convergence performance; 3) There is an optimal number of maximum aggregation times (communication rounds) in terms of convergence performance for a given protection level. Furthermore, we propose a K-random scheduling strategy, where K (1<K<N) clients are randomly selected from the N overall clients to participate in each aggregation. We also develop the corresponding convergence bound of the loss function in this case and the K-random scheduling strategy can also retain the above three properties. Moreover, we find that there is an optimal K that achieves the best convergence performance at a fixed privacy level. Evaluations demonstrate that our theoretical results are consistent with simulations, thereby facilitating the designs on various privacy-preserving FL algorithms with different tradeoff requirements on convergence performance and privacy levels.


Performance Analysis on Federated Learning with Differential Privacy

In this paper, to effectively prevent the differential attack, we propos...

Performance Analysis and Optimization in Privacy-Preserving Federated Learning

As a means of decentralized machine learning, federated learning (FL) ha...

Differentially Private Wireless Federated Learning Using Orthogonal Sequences

We propose a novel privacy-preserving uplink over-the-air computation (A...

Gain without Pain: Offsetting DP-injected Nosies Stealthily in Cross-device Federated Learning

Federated Learning (FL) is an emerging paradigm through which decentrali...

Blockchain Assisted Decentralized Federated Learning (BLADE-FL) with Lazy Clients

Federated learning (FL), as a distributed machine learning approach, has...

Gradient Sparsification for Efficient Wireless Federated Learning with Differential Privacy

Federated learning (FL) enables distributed clients to collaboratively t...

Trade Privacy for Utility: A Learning-Based Privacy Pricing Game in Federated Learning

To prevent implicit privacy disclosure in sharing gradients among data o...