Toward Autonomous and Efficient Cybersecurity: A Multi-Objective AutoML-based Intrusion Detection System

The proposed Intrusion Detection System (IDS) represents a significant advancement in cybersecurity, particularly as threats become more sophisticated and the Internet of Things (IoT) expands rapidly. By integrating Automated Machine Learning (AutoML) and Multi-Objective Optimization (MOO), the IDS framework addresses the pressing demand for efficient and scalable security solutions. It employs innovative techniques such as Optimized Importance and Percentage-based Automated Feature Selection (OIP-AutoFS) and Optimized Performance, Confidence, and Efficiency-based Combined Algorithm Selection and Hyperparameter Optimization (OPCE-CASH) to optimize feature selection and model learning processes. This approach not only enhances the effectiveness of intrusion detection but also improves computational efficiency, making it particularly suitable for resource-constrained IoT devices. Experimental evaluations demonstrate that this MOO-AutoML IDS outperforms existing state-of-the-art systems, …