A Grey Wolf Optimization-Based Ensemble Approach for High-Performance Attack Detection in IoT Infrastructures

This research presents an intrusion detection framework for Internet of Things (IoT) infrastructures using Grey Wolf Optimization-based feature selection, SMOTE for handling class imbalance, and an ensemble classifier combining Random Forest and Support Vector Machine. The proposed approach aims to improve attack detection accuracy while reducing the number of features and computational cost. Experimental results show that the model achieves high detection performance and is suitable for lightweight IoT security environments.