A hybrid improved binary GWO-PSO with random forest (IBGWO-PSO-RF) based intrusion detection model for large-scale attacks in IoT environment

The development of internet-connected environments to facilitate people to handle a variety of tasks is being made possible by the Internet of Things (IoT). Technology advancements offer businesses a numerous conveniences and benefits. However, they provide hackers and intruders more opportunities to investigate and take advantage of different methods to get through the security of IoT networks. Therefore, the primary challenges with the IoT based environments is security. It is essential to secure computer and Internet of Things platforms against a variety of threats and attacks. Furthermore, traditional intrusion detection systems (IDS) frequently handle massive amounts of data from IoT networks that contain redundant and irrelevant data, which results in decreased accuracy and longer response times. Therefore, this paper proposed an IDS to detect different types of attacks on IoT networks by employing the CIC-IoT-2023 dataset. The most relevant IoT network features are extracted by integrating the Improved Binary Grey Wolf Optimisation (IBGWO) and Particle Swarm Optimisation (PSO). Additionally, the Random Forest (RF) algorithm is used to analyse the selected features, using several decision trees to produce an accurate response. Therefore, the suggested Hybrid IBGWO-PSO-RF model has significantly outperformed the other IDS algorithms with an accuracy of 99.96% for multi-class classification.