Large Language Models Merging for Enhancing the Link Stealing Attack on Graph Neural Networks

TL;DR

This paper introduces a novel cross-dataset link stealing attack on Graph Neural Networks that leverages Large Language Models and model merging to improve attack effectiveness across multiple datasets and architectures.

Contribution

It proposes a new attack method combining cross-dataset knowledge and LLMs, along with a model merging technique to enhance attack generalization and effectiveness.

Findings

Merged attack model outperforms individual models on multiple datasets.

The approach is effective across different GNN and LLM architectures.

Cross-dataset and LLM-based attacks significantly increase privacy risks.

Abstract

Graph Neural Networks (GNNs), specifically designed to process the graph data, have achieved remarkable success in various applications. Link stealing attacks on graph data pose a significant privacy threat, as attackers aim to extract sensitive relationships between nodes (entities), potentially leading to academic misconduct, fraudulent transactions, or other malicious activities. Previous studies have primarily focused on single datasets and did not explore cross-dataset attacks, let alone attacks that leverage the combined knowledge of multiple attackers. However, we find that an attacker can combine the data knowledge of multiple attackers to create a more effective attack model, which can be referred to cross-dataset attacks. Moreover, if knowledge can be extracted with the help of Large Language Models (LLMs), the attack capability will be more significant. In this paper, we propose a novel link stealing attack method that takes advantage of cross-dataset and Large Language Models (LLMs). The LLM is applied to process datasets with different data structures in cross-dataset attacks. Each attacker fine-tunes the LLM on their specific dataset to generate a tailored attack model. We then introduce a novel model merging method to integrate the parameters of these attacker-specific models effectively. The result is a merged attack model with superior generalization capabilities, enabling effective attacks not only on the attackers' datasets but also on previously unseen (out-of-domain) datasets. We conducted extensive experiments in four datasets to demonstrate the effectiveness of our method. Additional experiments with three different GNN and LLM architectures further illustrate the generality of our approach.