Improved Differentially Private Decentralized Source Separation for fMRI Data
This work addresses privacy-preserving collaborative analysis of neuroimaging data for researchers, though it is incremental as it builds on existing decentralized and differentially private methods.
The authors tackled the problem of performing independent component analysis (ICA) on decentralized, privacy-sensitive fMRI data by proposing a differentially private algorithm that uses correlated noise to reduce noise compared to conventional methods. They demonstrated that their algorithm outperforms existing approaches on synthetic and real datasets and can sometimes achieve utility comparable to non-private algorithms.
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.