CAGCN: Causal attention graph convolutional network against adversarial attacks

초록

Have you ever been exposed to advertising accounts on social networks or distributed denial-of-service (DDoS) attacks? These attacks occur as intrusions in a network. Recently, several studies have demon-strated the vulnerability of graph convolutional networks (GCNs). In other words, given an abnormal graph with perturbations from a normal graph, the performance of GCNs drops significantly. To solve this problem, we propose a causal attention graph convolutional network (CAGCN). We design a causal graph where given data are affected by an attack and utilize the causal mechanism on GCNs to cut off the bias. Specifically, we use two types of attention, node attention (NoA) and neighbor attention (NeA), and demonstrate the robustness of our model, which does not significantly degrade the performance of the model as the attack becomes stronger. In addition, to show that the causal mechanism works well for robust learning, we apply the causal mechanism to the previous study and compared it.(c) 2023 Elsevier B.V. All rights reserved.

키워드