用于增强图神经网络链路窃取攻击的大语言模型融合
Large Language Models Merging for Enhancing the Link Stealing Attack on Graph Neural Networks
AI总结：
本研究提出一种结合跨数据集特性与大语言模型的新型链路窃取攻击方法，通过多攻击者专属LLM微调与模型融合，实现对已知及域外数据集的高效攻击，验证了方法的有效性与架构通用性。
摘要：
图神经网络（GNNs）是专门为处理图数据设计的模型，已在各类应用中取得了显著成效。针对图数据的链路窃取攻击会造成严重的隐私威胁，因为攻击者的目标是提取节点（实体）之间的敏感关系，这可能引发学术不端、欺诈交易或其他恶意行为。以往的研究主要聚焦于单一数据集，并未探索跨数据集攻击，更没有研究利用多个攻击者的组合知识开展攻击的场景。但我们发现，攻击者可以结合多个攻击者的数据知识，构建更高效的攻击模型，这类攻击可称为跨数据集攻击。此外，如果能借助大语言模型（LLMs）提取知识，攻击能力会进一步提升。本文提出了一种新型链路窃取攻击方法，该方法结合了跨数据集特性与大语言模型（LLMs）的优势。在跨数据集攻击中，我们利用LLM处理具有不同数据结构的数据集。每个攻击者在自己的特定数据集上微调LLM，生成定制化的攻击模型。随后我们提出了一种新型模型融合方法，可有效整合这些攻击者专属模型的参数。最终得到的融合攻击模型具备更优的泛化能力，不仅能对攻击者自身的数据集实施有效攻击，还能攻击此前未见过的（域外）数据集。我们在4个数据集上开展了大量实验，验证了所提方法的有效性。针对3种不同GNN和LLM架构的补充实验，进一步证明了我们方法的通用性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
