A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applications

TL;DR

This survey reviews privacy attacks and preservation techniques in Graph Neural Networks, highlighting current challenges and future directions for enhancing privacy without compromising utility.

Contribution

It provides a comprehensive overview of attack types, privacy-preserving methods, datasets, and applications in GNNs, filling a gap in existing literature.

Findings

Categorizes privacy attacks on GNNs by targeted information.

Summarizes privacy-preserving techniques in GNNs.

Identifies datasets and applications for privacy analysis.

Abstract

Graph Neural Networks (GNNs) have gained significant attention owing to their ability to handle graph-structured data and the improvement in practical applications. However, many of these models prioritize high utility performance, such as accuracy, with a lack of privacy consideration, which is a major concern in modern society where privacy attacks are rampant. To address this issue, researchers have started to develop privacy-preserving GNNs. Despite this progress, there is a lack of a comprehensive overview of the attacks and the techniques for preserving privacy in the graph domain. In this survey, we aim to address this gap by summarizing the attacks on graph data according to the targeted information, categorizing the privacy preservation techniques in GNNs, and reviewing the datasets and applications that could be used for analyzing/solving privacy issues in GNNs. We also outline potential directions for future research in order to build better privacy-preserving GNNs.