通过注入子图欺骗推荐系统，让目标节点被错误连接，破坏图神经网络分类效果。
LiSA: Leveraging Link Recommender to Attack Graph Neural Networks via Subgraph Injection
- 用孤立子图诱导链接推荐，制造虚假关联。
- 在真实数据集上使节点分类准确率显著下降，攻击成功率高。
- 适合研究图神经网络安全、对抗攻击的学者参考。
图神经网络（GNN）在建模图结构数据方面表现出色，但近期研究揭示其易受对抗攻击。传统攻击方法依赖修改原始图或向人工节点添加边，在真实场景中往往不切实际。本文提出一种新型对抗场景：通过注入孤立子图，误导链接推荐系统，使其建议将目标受害节点与子图之间建立连接，从而诱使用户无意中形成连接，导致节点分类准确率下降，实现成功攻击。为此，我们提出LiSA框架，采用双代理模型和两层优化策略，同时满足双重对抗目标。在多个真实世界数据集上的大量实验验证了该方法的有效性。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) have demonstrated remarkable proficiency in modeling data with graph structures, yet recent research reveals their susceptibility to adversarial attacks. Traditional attack methodologies, which rely on manipulating the original graph or adding links to artificially created nodes, often prove impractical in real-world settings. This paper introduces a novel adversarial scenario involving the injection of an isolated subgraph to deceive both the link recommender and the node classifier within a GNN system. Specifically, the link recommender is mislead to propose links between targeted victim nodes and the subgraph, encouraging users to unintentionally establish connections and that would degrade the node classification accuracy, thereby facilitating a successful attack. To address this, we present the LiSA framework, which employs a dual surrogate model and bi-level optimization to simultaneously meet two adversarial objectives. Extensive experiments on real-world datasets demonstrate the effectiveness of our method.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。