Classification of IoT intrusion detection data based on WGAN-gp and E-GraphSAGE

In recent years, the frequency and complexity of IoT network attacks have significantly increased. NIDS, strategically located in IoT network nodes, is an essential tool for monitoring traffic and detecting and mitigating network-based attacks. However, with the significant increase in computer network attacks, many datasets used for training suffer from imbalanced data problems. Therefore, to address the traffic characteristics of IoT networks and the issue of imbalanced data, this paper proposes an intrusion detection method that combines graph neural networks(E-GraphSAGE) and generative adversarial networks. Based on experiments using datasets NF-BoT-IoT, we found that training ML classifiers on datasets balanced with synthetic samples generated by WGAN-gp increased their prediction accuracy to 93.7% .