Improved Differentially Private Decentralized Source Separation for fMRI Data

TL;DR

This paper introduces a novel differentially private decentralized ICA algorithm for neuroimaging data, using correlated noise to improve utility and privacy preservation in small-sample, multi-site settings.

Contribution

It presents a new protocol employing correlated noise that enhances utility of private ICA in decentralized neuroimaging data analysis.

Findings

Outperforms existing private ICA methods on synthetic data

Achieves comparable utility to non-private algorithms in some cases

Demonstrates effectiveness on real neuroimaging datasets

Abstract

Blind source separation algorithms such as independent component analysis (ICA) are widely used in the analysis of neuroimaging data. In order to leverage larger sample sizes, different data holders/sites may wish to collaboratively learn feature representations. However, such datasets are often privacy-sensitive, precluding centralized analyses that pool the data at a single site. In this work, we propose a differentially private algorithm for performing ICA in a decentralized data setting. Conventional approaches to decentralized differentially private algorithms may introduce too much noise due to the typically small sample sizes at each site. We propose a novel protocol that uses correlated noise to remedy this problem. We show that our algorithm outperforms existing approaches on synthetic and real neuroimaging datasets and demonstrate that it can sometimes reach the same level of utility as the corresponding non-private algorithm. This indicates that it is possible to have meaningful utility while preserving privacy.