Lightweight Machine Learning-Based Intrusion Detection System for Securing IoT Networks

Abstract: The rapid expansion of the Internet of Things (IoT) has introduced significant security vulnerabilities, making IoT networks prime targets for cyberattacks. Conventional Intrusion Detection Systems (IDS) are often too resource-intensive for IoT environments due to their limited processing power, memory, and energy constraints. This study proposes a Lightweight Machine Learning-Based Intrusion Detection System (LML-IDS) designed to efficiently detect and mitigate security threats in IoT networks. The proposed model leverages feature selection and optimized algorithms such as Random Forest and Extreme Gradient Boosting (XGBoost) to enhance detection accuracy while minimizing computational overhead. Extensive experiments on benchmark IoT datasets demonstrate that the proposed IDS achieves high detection rates, reduced false positives, and improved energy efficiency compared to traditional systems. The framework ensures scalability, adaptability, and real-time intrusion detection, making it a practical solution for securing next-generation IoT ecosystems. Keywords: IoT Security, Intrusion Detection System (IDS), Machine Learning, Lightweight Algorithms, Anomaly Detection, Network Security, XGBoost, Random Forest, Edge Computing, Cybersecurity