Dopamine: Differentially Private Federated Learning on Medical Data

TL;DR

Dopamine is a federated learning system that uses differential privacy and secure aggregation to train deep neural networks on distributed medical data, achieving privacy guarantees close to centralized training with improved accuracy.

Contribution

It introduces Dopamine, a novel federated learning framework combining DPSGD and secure aggregation for privacy-preserving medical data analysis.

Findings

Achieves privacy guarantees close to centralized training.

Outperforms parallel DP FL in classification accuracy.

Demonstrates effectiveness on diabetic retinopathy dataset.

Abstract

While rich medical datasets are hosted in hospitals distributed across the world, concerns on patients' privacy is a barrier against using such data to train deep neural networks (DNNs) for medical diagnostics. We propose Dopamine, a system to train DNNs on distributed datasets, which employs federated learning (FL) with differentially-private stochastic gradient descent (DPSGD), and, in combination with secure aggregation, can establish a better trade-off between differential privacy (DP) guarantee and DNN's accuracy than other approaches. Results on a diabetic retinopathy~(DR) task show that Dopamine provides a DP guarantee close to the centralized training counterpart, while achieving a better classification accuracy than FL with parallel DP where DPSGD is applied without coordination. Code is available at https://github.com/ipc-lab/private-ml-for-health.