Two-Phase Multi-Party Computation Enabled Privacy-Preserving Federated Learning

TL;DR

This paper introduces a two-phase multi-party computation approach to enhance privacy-preserving federated learning, reducing communication costs and improving scalability for IoT applications in smart manufacturing.

Contribution

It proposes a novel two-phase MPC-enabled federated learning framework with committee-based model aggregation to improve scalability and efficiency.

Findings

Achieves privacy-preserving model aggregation with reduced communication overhead.

Maintains high model accuracy comparable to traditional methods.

Demonstrates effectiveness in an IoT smart manufacturing platform.

Abstract

Countries across the globe have been pushing strict regulations on the protection of personal or private data collected. The traditional centralized machine learning method, where data is collected from end-users or IoT devices, so that it can discover insights behind real-world data, may not be feasible for many data-driven industry applications in light of such regulations. A new machine learning method, coined by Google as Federated Learning (FL) enables multiple participants to train a machine learning model collectively without directly exchanging data. However, recent studies have shown that there is still a possibility to exploit the shared models to extract personal or confidential data. In this paper, we propose to adopt Multi Party Computation (MPC) to achieve privacy-preserving model aggregation for FL. The MPC-enabled model aggregation in a peer-to-peer manner incurs high communication overhead with low scalability. To address this problem, the authors proposed to develop a two-phase mechanism by 1) electing a small committee and 2) providing MPC-enabled model aggregation service to a larger number of participants through the committee. The MPC enabled FL framework has been integrated in an IoT platform for smart manufacturing. It enables a set of companies to train high quality models collectively by leveraging their complementary data-sets on their own premises, without compromising privacy, model accuracy vis-a-vis traditional machine learning methods and execution efficiency in terms of communication cost and execution time.