IOT Network Malicious Session Detection By Genetic Feature Optimization Algorithm

Authors: Rishav Kumar Mishra, Prof. Sujeet Gautam, Prof. S Vishwakarma

Abstract: The rapid growth of Internet of Things (IoT) networks has significantly improved human comfort and quality of life. However, this expansion has also increased vulnerability to cyber intrusions, making IoT security a critical concern. This work proposes an IoT network intrusion detection system that classifies network sessions into normal and attack categories. A Genetic Algorithm (GA) is employed for optimal feature selection, enabling the identification of the most representative session attributes for accurate classification. The selected features are then utilized by the K-Nearest Neighbour (KNN) classifier to detect intrusions effectively. Experiments conducted on a real-world dataset demonstrate that the proposed GA-based IoT Network Security model significantly enhances detection accuracy and optimizes key evaluation performance metrics.