Differential Privacy-enabled Federated Learning for Sensitive Health Data

TL;DR

This paper presents a federated learning framework for healthcare data that ensures privacy through data localization and differential privacy, enabling collaborative model training without exposing sensitive patient information.

Contribution

It introduces a novel federated learning approach with differential privacy tailored for sensitive health data, addressing practical privacy and resource challenges.

Findings

Effective privacy protection with differential privacy

Maintains high utility of the global model

Scalable to large healthcare datasets

Abstract

Leveraging real-world health data for machine learning tasks requires addressing many practical challenges, such as distributed data silos, privacy concerns with creating a centralized database from person-specific sensitive data, resource constraints for transferring and integrating data from multiple sites, and risk of a single point of failure. In this paper, we introduce a federated learning framework that can learn a global model from distributed health data held locally at different sites. The framework offers two levels of privacy protection. First, it does not move or share raw data across sites or with a centralized server during the model training process. Second, it uses a differential privacy mechanism to further protect the model from potential privacy attacks. We perform a comprehensive evaluation of our approach on two healthcare applications, using real-world electronic health data of 1 million patients. We demonstrate the feasibility and effectiveness of the federated learning framework in offering an elevated level of privacy and maintaining utility of the global model.