Unveiling the Role of Message Passing in Dual-Privacy Preservation on GNNs

TL;DR

This paper investigates how message passing in GNNs contributes to privacy leakage and proposes a dual-privacy preservation framework that effectively protects node and link privacy while maintaining utility.

Contribution

The study reveals the role of message passing in privacy leakage and introduces a novel framework with three modules to safeguard dual privacy in GNNs.

Findings

Message passing under structural bias amplifies privacy leakage.

The proposed framework effectively protects node and link privacy.

Experimental results show high utility retention with privacy safeguards.

Abstract

Graph Neural Networks (GNNs) are powerful tools for learning representations on graphs, such as social networks. However, their vulnerability to privacy inference attacks restricts their practicality, especially in high-stake domains. To address this issue, privacy-preserving GNNs have been proposed, focusing on preserving node and/or link privacy. This work takes a step back and investigates how GNNs contribute to privacy leakage. Through theoretical analysis and simulations, we identify message passing under structural bias as the core component that allows GNNs to \textit{propagate} and \textit{amplify} privacy leakage. Building upon these findings, we propose a principled privacy-preserving GNN framework that effectively safeguards both node and link privacy, referred to as dual-privacy preservation. The framework comprises three major modules: a Sensitive Information Obfuscation Module that removes sensitive information from node embeddings, a Dynamic Structure Debiasing Module that dynamically corrects the structural bias, and an Adversarial Learning Module that optimizes the privacy-utility trade-off. Experimental results on four benchmark datasets validate the effectiveness of the proposed model in protecting both node and link privacy while preserving high utility for downstream tasks, such as node classification.