Secure Neuroimaging Analysis using Federated Learning with Homomorphic Encryption

TL;DR

This paper presents a secure federated learning framework for neuroimaging data using homomorphic encryption, enabling privacy-preserving model training without performance loss on large-scale MRI datasets.

Contribution

It introduces a fully-homomorphic encryption-based framework for federated learning that maintains model accuracy while enhancing data privacy in neuroimaging applications.

Findings

No degradation in model performance with encryption

Effective training on large-scale MRI datasets

Enhanced privacy protection in federated neuroimaging analysis

Abstract

Federated learning (FL) enables distributed computation of machine learning models over various disparate, remote data sources, without requiring to transfer any individual data to a centralized location. This results in an improved generalizability of models and efficient scaling of computation as more sources and larger datasets are added to the federation. Nevertheless, recent membership attacks show that private or sensitive personal data can sometimes be leaked or inferred when model parameters or summary statistics are shared with a central site, requiring improved security solutions. In this work, we propose a framework for secure FL using fully-homomorphic encryption (FHE). Specifically, we use the CKKS construction, an approximate, floating point compatible scheme that benefits from ciphertext packing and rescaling. In our evaluation on large-scale brain MRI datasets, we use our proposed secure FL framework to train a deep learning model to predict a person's age from distributed MRI scans, a common benchmarking task, and demonstrate that there is no degradation in the learning performance between the encrypted and non-encrypted federated models.