Privacy Guarantee for Nash Equilibrium Computation of Aggregative Games Based on Pointwise Maximal Leakage

TL;DR

This paper introduces a pointwise maximal leakage framework for privacy-preserving Nash equilibrium computation in aggregative games, providing tighter privacy guarantees than differential privacy, especially for correlated datasets.

Contribution

It develops a PML-based privacy guarantee method that refines differential privacy and effectively handles dataset correlations in NE computation.

Findings

PML offers a tighter privacy guarantee than DP.

Lower bounds of PML can surpass DP upper bounds in correlated datasets.

Experimental results demonstrate the framework's effectiveness against inference attacks.

Abstract

Privacy preservation has served as a key metric in designing Nash equilibrium (NE) computation algorithms. Although differential privacy (DP) has been widely employed for privacy guarantees, it does not exploit prior distributional knowledge of datasets and is ineffective in assessing information leakage for correlated datasets. To address these concerns, we establish a pointwise maximal leakage (PML) framework when computing NE in aggregative games. By incorporating prior knowledge of players' cost function datasets, we obtain a precise and computable upper bound of privacy leakage with PML guarantees. In the entire view, we show PML refines DP by offering a tighter privacy guarantee, enabling flexibility in designing NE computation. Also, in the individual view, we reveal that the lower bound of PML can exceed the upper bound of DP by constructing specific correlated datasets. The results emphasize that PML is a more proper privacy measure than DP since the latter fails to adequately capture privacy leakage in correlated datasets. Moreover, we conduct experiments with adversaries who attempt to infer players' private information to illustrate the effectiveness of our framework.