Evaluating the Strength of Genomic Privacy Metrics

TL;DR

This paper critically evaluates existing genomic privacy metrics, highlighting their shortcomings, and offers guidelines for better metric selection, interpretation, and visualization through a case study on Alzheimer's disease.

Contribution

It identifies issues with current genomic privacy metrics and proposes improved methods for measuring and interpreting privacy in genomic data.

Findings

Many existing metrics are not monotonic with adversary strength

Some metrics can be misleading or inconsistent in privacy assessment

Guidelines improve the reliability of genomic privacy evaluation

Abstract

The genome is a unique identifier for human individuals. The genome also contains highly sensitive information, creating a high potential for misuse of genomic data (for example, genetic discrimination). In this paper, I investigated how genomic privacy can be measured in scenarios where an adversary aims to infer a person's genomic markers by constructing probability distributions on the values of genetic variations. I measured the strength of privacy metrics by requiring that metrics are monotonic with increasing adversary strength and uncovered serious problems with several existing metrics currently used to measure genomic privacy. I provide suggestions on metric selection, interpretation, and visualization, and illustrate the work flow using a case study on Alzheimer's disease.