Privacy-preserving collaborative machine learning on genomic data using TensorFlow

TL;DR

This paper presents a TensorFlow-based framework for privacy-preserving collaborative machine learning on genomic data, utilizing secure multi-party computation to enable sensitive data analysis without compromising privacy.

Contribution

It introduces MPC-friendly ML primitives and extends TF Encrypted, improving experimental flexibility and performance in privacy-preserving genomic analysis.

Findings

Achieved first place in iDASH2019 secure genome analysis competition.

Developed scalable MPC primitives compatible with TensorFlow.

Demonstrated competitive performance against state-of-the-art methods.

Abstract

Machine learning (ML) methods have been widely used in genomic studies. However, genomic data are often held by different stakeholders (e.g. hospitals, universities, and healthcare companies) who consider the data as sensitive information, even though they desire to collaborate. To address this issue, recent works have proposed solutions using Secure Multi-party Computation (MPC), which train on the decentralized data in a way that the participants could learn nothing from each other beyond the final trained model. We design and implement several MPC-friendly ML primitives, including class weight adjustment and parallelizable approximation of activation function. In addition, we develop the solution as an extension to TF Encrypted~\citep{dahl2018private}, enabling us to quickly experiment with enhancements of both machine learning techniques and cryptographic protocols while leveraging the advantages of TensorFlow's optimizations. Our implementation compares favorably with state-of-the-art methods, winning first place in Track IV of the iDASH2019 secure genome analysis competition.