A Note on Our Submission to Track 4 of iDASH 2019

TL;DR

This paper describes a solution for privacy-preserving machine learning training on biological data using multi-party computation, achieving fast training times with acceptable accuracy in a cryptographic competition.

Contribution

It presents an efficient MPC implementation for cancer research data training, demonstrating practical performance on cloud infrastructure.

Findings

Training completed in under one minute on AWS instances.

Achieved training in less than ten seconds with slightly reduced accuracy.

Demonstrated feasibility of MPC for real-world biological data analysis.

Abstract

iDASH is a competition soliciting implementations of cryptographic schemes of interest in the context of biology. In 2019, one track asked for multi-party computation implementations of training of a machine learning model suitable for two datasets from cancer research. In this note, we describe our solution submitted to the competition. We found that the training can be run on three AWS c5.9xlarge instances in less then one minute using MPC tolerating one semi-honest corruption, and less than ten seconds at a slightly lower accuracy.