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

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