An Advanced Intrusion Detection System for IIoT Based on GA and Tree Based Algorithms

The evolution of the Internet and cloud-based technologies have empowered several organizations with capacity to implement large-scale Things (IoT)-based ecosystems, such as Industrial IoT (IIoT). and, by virtue, IIoT, are vulnerable new types threats intrusions because nature their networks. So it is crucial develop Intrusion Detection Systems (IDSs) that can provide security, privacy, integrity IIoT In this research, we propose an IDS for was implemented using Genetic Algorithm (GA) feature selection, Random Forest (RF) model employed in GA fitness function. models used intrusion detection processes include classifiers RF, Linear Regression (LR), Naïve Bayes (NB), Decision Tree (DT), Extra-Trees (ET), Extreme Gradient Boosting (XGB). GA-RF generated 10 vectors binary classification scheme 7 multiclass procedure. UNSW-NB15 assess effectiveness robustness our proposed approach. experimental outcomes demonstrated modeling process, achieved a test accuracy (TAC) 87.61% Area Under Curve (AUC) 0.98, vector contained 16 features. These results were superior existing frameworks.