论文标题
检测针对图神经网络的拓扑攻击
Detecting Topology Attacks against Graph Neural Networks
论文作者
论文摘要
图形神经网络（GNN）已在许多实际应用中广泛使用，最近的研究揭示了它们针对拓扑攻击的脆弱性。为了解决这个问题，现有的努力主要致力于改善GNN的鲁棒性，而对检测此类攻击的关注很少。在这项工作中，我们研究了对GNN拓扑攻击的受害者节点检测问题。我们的方法建立在植根于GNN的固有信息中的关键观察基础上。也就是说，受害者节点的邻居倾向于具有两个竞争性的组力，将节点分类结果分别推向原始标签和目标标签。基于此观察结果，我们建议通过故意设计每个节点的邻域差异来检测受害者节点。对四个现实世界数据集和五次现有拓扑攻击的广泛实验结果表明了拟议检测方法的有效性和效率。
Graph neural networks (GNNs) have been widely used in many real applications, and recent studies have revealed their vulnerabilities against topology attacks. To address this issue, existing efforts have mainly been dedicated to improving the robustness of GNNs, while little attention has been paid to the detection of such attacks. In this work, we study the victim node detection problem under topology attacks against GNNs. Our approach is built upon the key observation rooted in the intrinsic message passing nature of GNNs. That is, the neighborhood of a victim node tends to have two competing group forces, pushing the node classification results towards the original label and the targeted label, respectively. Based on this observation, we propose to detect victim nodes by deliberately designing an effective measurement of the neighborhood variance for each node. Extensive experimental results on four real-world datasets and five existing topology attacks show the effectiveness and efficiency of the proposed detection approach.
