Intrusion Detection System for IoT Networks
V. Jyothsna, E. Sandhya, R Roopa, B. Deena Divya Nayomi, D. K. Shareef, P. Bhasha
Abstract
In today’s modern society, technology in networks and other technological IoT advancements have become deeply rooted. However, with the development of the usage of these technologies in businesses and individuals are constantly at risk of cyber threats. Safeguard system security and intrusion detection systems (IDS) play a crucial role. Despite their importance, IDS still faces challenges in improving its classification performance. To overcome this issue, this paper states an advanced approach for designing IDS for IoT networks that employ the Chimpanzees Optimization Algorithm for feature optimization and stacking algorithm for classification. The intrusion detection process utilizes Random Forest (RF), K-Nearest Neighbor (KNN), and XGBoost classifiers, with logistic regression being the meta-classifier. To calculate the efficiency and strength of the proposed system, IoT-23 is utilized. The final output shows that this suggested methodology can effectively detect attacks in networks, thereby enhancing the privacy of IoT networks. Moreover, with the rapid advancement of IoT technology, it has become essential to avoid attacks on computers and networks of IoT from various breaches and thefts, and this approach can prove useful in achieving this goal.