Binary Federated Learning with Client-Level Differential Privacy

TL;DR

This paper introduces a communication-efficient federated learning algorithm using binary neural networks and discrete noise to enhance privacy and performance, reducing communication costs while providing client-level differential privacy.

Contribution

It proposes a novel FL training method with binary models and discrete noise, improving privacy-utility trade-off and communication efficiency over existing Gaussian mechanisms.

Findings

Achieves client-level differential privacy with performance gains.

Reduces communication overhead using binary neural networks.

Demonstrates effectiveness on MNIST and Fashion-MNIST datasets.

Abstract

Federated learning (FL) is a privacy-preserving collaborative learning framework, and differential privacy can be applied to further enhance its privacy protection. Existing FL systems typically adopt Federated Average (FedAvg) as the training algorithm and implement differential privacy with a Gaussian mechanism. However, the inherent privacy-utility trade-off in these systems severely degrades the training performance if a tight privacy budget is enforced. Besides, the Gaussian mechanism requires model weights to be of high-precision. To improve communication efficiency and achieve a better privacy-utility trade-off, we propose a communication-efficient FL training algorithm with differential privacy guarantee. Specifically, we propose to adopt binary neural networks (BNNs) and introduce discrete noise in the FL setting. Binary model parameters are uploaded for higher communication efficiency and discrete noise is added to achieve the client-level differential privacy protection. The achieved performance guarantee is rigorously proved, and it is shown to depend on the level of discrete noise. Experimental results based on MNIST and Fashion-MNIST datasets will demonstrate that the proposed training algorithm achieves client-level privacy protection with performance gain while enjoying the benefits of low communication overhead from binary model updates.