SoK: Differential Privacy on Graph-Structured Data

TL;DR

This paper systematically reviews how differential privacy can be applied to graph-structured data, addressing the unique challenges posed by interconnected data points and GNNs, and highlights open research questions.

Contribution

It provides a comprehensive systematisation of differential privacy formulations for graphs and GNNs, and discusses challenges and future research directions.

Findings

Different DP formulations for graphs are compared and categorized.

Challenges in applying DP to interconnected data are identified.

Open questions for future research in graph privacy are discussed.

Abstract

In this work, we study the applications of differential privacy (DP) in the context of graph-structured data. We discuss the formulations of DP applicable to the publication of graphs and their associated statistics as well as machine learning on graph-based data, including graph neural networks (GNNs). The formulation of DP in the context of graph-structured data is difficult, as individual data points are interconnected (often non-linearly or sparsely). This connectivity complicates the computation of individual privacy loss in differentially private learning. The problem is exacerbated by an absence of a single, well-established formulation of DP in graph settings. This issue extends to the domain of GNNs, rendering private machine learning on graph-structured data a challenging task. A lack of prior systematisation work motivated us to study graph-based learning from a privacy perspective. In this work, we systematise different formulations of DP on graphs, discuss challenges and promising applications, including the GNN domain. We compare and separate works into graph analysis tasks and graph learning tasks with GNNs. Finally, we conclude our work with a discussion of open questions and potential directions for further research in this area.