LinkThief: Combining Generalized Structure Knowledge with Node Similarity for Link Stealing Attack against GNN

TL;DR

LinkThief introduces a novel attack method that combines generalized structure knowledge with node similarity, effectively stealing links in GNNs even when traditional assumptions do not hold, by leveraging shadow and target graph insights.

Contribution

It proposes a new link stealing attack framework that integrates generalized structure knowledge with node similarity using a Shadow-Target Bridge Graph, enhancing attack effectiveness.

Findings

Effective link stealing without extra assumptions

Utilizes Shadow-Target Bridge Graph for better structure understanding

Outperforms existing methods in experimental validation

Abstract

Graph neural networks(GNNs) have a wide range of applications in multimedia.Recent studies have shown that Graph neural networks(GNNs) are vulnerable to link stealing attacks,which infers the existence of edges in the target GNN's training graph.Existing attacks are usually based on the assumption that links exist between two nodes that share similar posteriors;however,they fail to focus on links that do not hold under this assumption.To this end,we propose LinkThief,an improved link stealing attack that combines generalized structure knowledge with node similarity,in a scenario where the attackers' background knowledge contains partially leaked target graph and shadow graph.Specifically,to equip the attack model with insights into the link structure spanning both the shadow graph and the target graph,we introduce the idea of creating a Shadow-Target Bridge Graph and extracting edge subgraph structure features from it.Through theoretical analysis from the perspective of privacy theft,we first explore how to implement the aforementioned ideas.Building upon the findings,we design the Bridge Graph Generator to construct the Shadow-Target Bridge Graph.Then,the subgraph around the link is sampled by the Edge Subgraph Preparation Module.Finally,the Edge Structure Feature Extractor is designed to obtain generalized structure knowledge,which is combined with node similarity to form the features provided to the attack model.Extensive experiments validate the correctness of theoretical analysis and demonstrate that LinkThief still effectively steals links without extra assumptions.