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.
翻译:在许多实际应用中广泛使用脑电图网络(GNNs),最近的研究揭示了这些网络对地形攻击的脆弱性。为解决这一问题,现有努力主要致力于提高GNNs的稳健性,但很少注意这类攻击的检测。在这项工作中,我们在对GNS的地形攻击中研究了受害者节点探测问题。我们的方法基于根植于GNS传传传的内在信息的关键观察。这就是说,受害者节点的周围往往有两种相互竞争的团体力量,分别将节点分类结果推向原始标签和目标标签。基于这一观察,我们提议对受害者节点进行检测,刻意为每个节点设计有效的社区差异测量。关于四个现实世界数据集和五个现有地形攻击的广泛实验结果显示了拟议探测方法的有效性和效率。