Despite the success of graph neural networks (GNNs) in various domains, they exhibit susceptibility to adversarial attacks. Understanding these vulnerabilities is crucial for developing robust and secure applications. In this paper, we investigate the impact of test time adversarial attacks through edge perturbations which involve both edge insertions and deletions. A novel explainability-based method is proposed to identify important nodes in the graph and perform edge perturbation between these nodes. The proposed method is tested for node classification with three different architectures and datasets. The results suggest that introducing edges between nodes of different classes has higher impact as compared to removing edges among nodes within the same class.

翻译：尽管图神经网络（GNN）在多个领域取得了成功，但它们表现出对对抗攻击的敏感性。理解这些脆弱性对于开发鲁棒且安全的应用至关重要。本文研究了通过边扰动（包括边插入和删除）进行的测试时对抗攻击的影响。我们提出了一种新颖的基于可解释性的方法，用于识别图中的重要节点，并在这些节点之间执行边扰动。所提方法在三种不同架构和数据集上针对节点分类任务进行了测试。结果表明，在不同类别的节点之间引入边比删除同一类别节点之间的边具有更高的影响。