A Lightweight Security Decision Framework for IoT Intrusion Detection Using Entropy-Guided Feature Integrity and Adaptive Ensemble Learning
The rapid growth of the Internet of Things (IoT) has intensified cybersecurity risks while exposing the limitations of traditional security solutions in resource-constrained environments. Intrusion detection in IoT systems, therefore, requires reliable, real-time decision-making with minimal computational overhead. This paper presents a lightweight IoT security decision framework that combines entropy-guided feature selection with an adaptive ensemble-based intrusion detection strategy. The proposed approach employs an entropy–correlation (EnCor) feature selection pipeline to construct a compact and informative feature subset, reducing complexity while preserving discriminative security characteristics. Detection decisions are generated using a soft voting ensemble of complementary machine learning classifiers, supported by an adaptive fallback mechanism to improve reliability under diverse attack scenarios. The framework is specifically designed for edge- and gateway-level IoT deployment, avoiding the high latency and computational demands associated with deep learning and blockchain-based solutions. Experimental evaluation on the TON_IoT and CICIoT2023 datasets demonstrates high detection accuracy with low inference latency and reduced memory consumption. The results confirm that effective intrusion detection can be achieved without compromising practical deployment feasibility. Overall, the proposed framework establishes intrusion detection as an efficient and deployable security decision layer for real-world IoT environments.