DNA: Differentially private Neural Augmentation for contact tracing

TL;DR

This paper introduces a neural augmentation method for contact tracing that ensures differential privacy, significantly improving infection detection and testing efficiency while safeguarding user privacy.

Contribution

It presents a novel neural network-based augmentation for contact tracing that guarantees differential privacy, enhancing detection accuracy over previous statistical inference methods.

Findings

Improved detection of infected individuals at epsilon=1 privacy level

Reduced infection rates through targeted testing in simulations

First integration of deep learning with privacy guarantees in contact tracing

Abstract

The COVID19 pandemic had enormous economic and societal consequences. Contact tracing is an effective way to reduce infection rates by detecting potential virus carriers early. However, this was not generally adopted in the recent pandemic, and privacy concerns are cited as the most important reason. We substantially improve the privacy guarantees of the current state of the art in decentralized contact tracing. Whereas previous work was based on statistical inference only, we augment the inference with a learned neural network and ensure that this neural augmentation satisfies differential privacy. In a simulator for COVID19, even at epsilon=1 per message, this can significantly improve the detection of potentially infected individuals and, as a result of targeted testing, reduce infection rates. This work marks an important first step in integrating deep learning into contact tracing while maintaining essential privacy guarantees.