SoK: Differential Privacy on Graph-Structured Data
read the original 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.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Bayesian Membership Privacy for Graph Neural Networks
Introduces Bayesian Membership Privacy (BMP) as a sampling-aware node-level privacy definition for GNNs quantified by posterior membership probability, plus an auditing method and benchmark experiments.
-
SoK: Practical Aspects of Releasing Differentially Private Graphs
The authors provide a systematization of differentially private graph release methods along with an objective-based framework and two illustrative evaluations for social network analysts.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.