XGBoost for Imbalanced Multiclass Classification-Based Industrial Internet of Things Intrusion Detection Systems

Abstract

The Industrial Internet of Things (IIoT) has advanced digital technology and the fastest interconnection, which creates opportunities to substantially grow industrial businesses today. Although IIoT provides promising opportunities for growth, the massive sensor IoT data collected are easily attacked by cyber criminals. Hence, IIoT requires different high security levels to protect the network. An Intrusion Detection System (IDS) is one of the crucial security solutions, which aims to detect the network’s abnormal behavior and monitor safe network traffic to avoid attacks. In particular, the effectiveness of the Machine Learning (ML)-based IDS approach to building a secure IDS application is attracting the security research community in both the general cyber network and the specific IIoT network. However, most available IIoT datasets contain multiclass output data with imbalanced distributions. This is the main reason for the reduction in the detection accuracy of attacks of the ML-based IDS model. This research proposes an IDS for IIoT imbalanced datasets by applying the eXtremely Gradient Boosting (XGBoost) model to overcome this issue. Two modern IIoT imbalanced datasets were used to assess our proposed method’s effectiveness and robustness, X-IIoTDS and TON_IoT. The XGBoost model achieved excellent attack detection with F1 scores of 99.9% and 99.87% on the two datasets. This result demonstrated that the proposed approach improved the detection attack performance in imbalanced multiclass IIoT datasets and was superior to existing IDS frameworks.