Swarm intelligence for intrusion detection systems in internet of things environments

Abstract

The rise of the internet of things (IoT) technology has brought new security challenges, necessitating robust intrusion detection systems (IDS). This research applies swarm intelligence (SI) principles, specifically the pigeon inspired optimization (PIO) algorithm, to enhance IDS effectiveness in IoT environments. Drawing on the behavior of social species, SI fosters decentralized control and emergent behavior from simple rules. These principles guide the PIO algorithm, making it apt for optimizing IDS. We utilize two comprehensive IoT datasets – the Canadian Institute for Cybersecurity (CIC) IoT dataset 2023 and the IoT dataset for IDS, aiming to boost the IDS’s capability to detect illicit attacks. By adapting the PIO algorithm, our IDS learns from the environment, adapts to evolving threats, and mitigates false-positive rates. Preliminary tests show that our SI-based IDS outperforms traditional systems’ accuracy, speed, and adaptability. This research advances SI applications in IoT security, contributing to developing more resilient IDS and ultimately enhancing IoT network security against a range of cyber threats.