Differentially Private Secure Multi-Party Computation for Federated Learning in Financial Applications

TL;DR

This paper introduces a privacy-preserving federated learning protocol combining differential privacy and secure multiparty computation, specifically designed for financial applications, demonstrated with logistic regression on credit card fraud data.

Contribution

It presents a novel federated learning system integrating differential privacy and secure multiparty computation, tailored for financial data privacy and collaborative model training.

Findings

Effective privacy protection in federated learning for finance

Maintains model accuracy with combined privacy techniques

Validated with real-world credit card fraud dataset

Abstract

Federated Learning enables a population of clients, working with a trusted server, to collaboratively learn a shared machine learning model while keeping each client's data within its own local systems. This reduces the risk of exposing sensitive data, but it is still possible to reverse engineer information about a client's private data set from communicated model parameters. Most federated learning systems therefore use differential privacy to introduce noise to the parameters. This adds uncertainty to any attempt to reveal private client data, but also reduces the accuracy of the shared model, limiting the useful scale of privacy-preserving noise. A system can further reduce the coordinating server's ability to recover private client information, without additional accuracy loss, by also including secure multiparty computation. An approach combining both techniques is especially relevant to financial firms as it allows new possibilities for collaborative learning without exposing sensitive client data. This could produce more accurate models for important tasks like optimal trade execution, credit origination, or fraud detection. The key contributions of this paper are: We present a privacy-preserving federated learning protocol to a non-specialist audience, demonstrate it using logistic regression on a real-world credit card fraud data set, and evaluate it using an open-source simulation platform which we have adapted for the development of federated learning systems.