Homomorphic Encryption and Federated Learning based Privacy-Preserving CNN Training: COVID-19 Detection Use-Case

TL;DR

This paper introduces a privacy-preserving federated learning approach for medical data that employs homomorphic encryption and secure multi-party computation to protect sensitive information during CNN training for COVID-19 detection.

Contribution

It proposes a novel federated learning algorithm enhanced with homomorphic encryption and secure computation to safeguard medical data against privacy attacks.

Findings

Effective model performance on real-world medical data

Enhanced privacy protection against adversarial attacks

Feasible implementation of privacy-preserving CNN training

Abstract

Medical data is often highly sensitive in terms of data privacy and security concerns. Federated learning, one type of machine learning techniques, has been started to use for the improvement of the privacy and security of medical data. In the federated learning, the training data is distributed across multiple machines, and the learning process is performed in a collaborative manner. There are several privacy attacks on deep learning (DL) models to get the sensitive information by attackers. Therefore, the DL model itself should be protected from the adversarial attack, especially for applications using medical data. One of the solutions for this problem is homomorphic encryption-based model protection from the adversary collaborator. This paper proposes a privacy-preserving federated learning algorithm for medical data using homomorphic encryption. The proposed algorithm uses a secure multi-party computation protocol to protect the deep learning model from the adversaries. In this study, the proposed algorithm using a real-world medical dataset is evaluated in terms of the model performance.