An Intelligent Feature Selection Technique through Combining Genetic and Grey Wolf Algorithms to Advance a Lightweight Intrusion Detection for Wireless Networks in IoT

Document Type: Original Article


1 Faculty of electrical and computer engineering, Qom university of technology Qom, Iran

2 Department of Computer Engineering, Qom Branch, Islamic Azad University, Qom, Iran

3 Faculty of Electrical, Computer, and Biomedical Engineering, Shahabdanesh University



The rapid increase in the number and diversity of smart devices connected to the internet, usually through open wireless sensor networks (WSNs), in internet of things (IoT) has led to the fact, that attackers can easily intercept, eavesdrop, and rebroadcast network traffic. Intrusion detection system (IDS) is a key security solution, however despite the maturity of IDS methodology for traditional networks, current technologies with high computational complexity are improper for resource-limited WSNs in IoT and also they fail to detect new WSN attacks. Furtheremore, dealing with the huge amount of intrusion wireless traffic collected by sensors, causing slow detecting process, higher resource usage and inaccurate detection. Hence, considering WSN limitations for developing an IDS in IoT, establishes a significant challenge for security researchers. This paper proposes a new model to develop a lightweight IDS(LIDS) using combination of genetic algorithm (GA) and grey wolf optimizer (GWO) termed as GAGWO. The GAGWO tries to find the most relevant traffic features and eliminate worthless ones intelligently, in order to increase the performance of the LIDS. The performance of LIDS is evaluated using AWID real-world wireless dataset under two scenarios with and without using GAGWO. Experimental results proved that GAGWO individually not only improved the performance of the LIDS in terms of computational costs but it also enabled it to detect with high accuracy and low false alarm rate. Besides, GAGWO in comparison to the original GA and GWO and other recent existing methods like FWP-SVM-GA and BGWO has shown to be more prominent.


Main Subjects