# Disparate Vulnerability to Membership Inference Attacks

## TL;DR

This paper investigates the unequal susceptibility of different population groups to membership inference attacks, establishing conditions for prevention, analyzing connections to fairness and privacy, and providing a framework for reliable assessment.

## Contribution

It offers a theoretical framework for understanding and measuring disparate vulnerability to MIAs, linking it to fairness and privacy, and presents experimental evidence of such disparities.

## Key findings

- Disparate vulnerability exists in realistic settings.
- Fairness alone cannot prevent all disparities.
- Differential privacy reduces but does not eliminate vulnerability.

## Abstract

A membership inference attack (MIA) against a machine-learning model enables an attacker to determine whether a given data record was part of the model's training data or not. In this paper, we provide an in-depth study of the phenomenon of disparate vulnerability against MIAs: unequal success rate of MIAs against different population subgroups. We first establish necessary and sufficient conditions for MIAs to be prevented, both on average and for population subgroups, using a notion of distributional generalization. Second, we derive connections of disparate vulnerability to algorithmic fairness and to differential privacy. We show that fairness can only prevent disparate vulnerability against limited classes of adversaries. Differential privacy bounds disparate vulnerability but can significantly reduce the accuracy of the model. We show that estimating disparate vulnerability to MIAs by na\"ively applying existing attacks can lead to overestimation. We then establish which attacks are suitable for estimating disparate vulnerability, and provide a statistical framework for doing so reliably. We conduct experiments on synthetic and real-world data finding statistically significant evidence of disparate vulnerability in realistic settings. The code is available at https://github.com/spring-epfl/disparate-vulnerability