Hybridizing genetic algorithm and grey wolf optimizer to advance an intelligent and lightweight intrusion detection system for IoT wireless networks

Open wireless sensor networks (WSNs) in Internet of things (IoT) has led to many zero-day security attacks. Since intrusion detection is a key security solution, this paper presents a lightweight machine learning-based intrusion detection technique with high performance for resource limited IoT wireless networks namely, IoT intrusion detection system (IoTIDS). IoTIDS is based on hybridization of genetic algorithm (GA) and grey wolf optimizer (GWO), termed as GA–GWO. The main aim of the hybrid algorithm for the IoTIDS is to reduce the dimensionality of the huge wireless network traffic through intelligent selecting the most informative traffic features. By hybridizing, we try to eliminate their weaknesses through GA and GWO strengths. The effectiveness of the GA–GWO on IoTIDS is evaluated using AWID (aegean wi-fi intrusion dataset) as a new real-world wireless intrusion dataset, after preprocessing it under different scenarios. The experimental results proved that the proposed GA–GWO individually not only improved the performance of the IoTIDS in terms of computational costs, but it also enabled the IoTIDS to detect ? with high accuracy and low false alarm rate. Furthermore, GA–GWO in comparison to the original GA and GWO and other recent existing methods like FS, weight, and parameter optimization of SVM based on the GA (FWP-SVM-GA) and binary GWO (BGWO) has proven to be more effective.