A Systematic Literature Review on Swarm Intelligence Based Intrusion Detection System: Past, Present and Future

Swarm Intelligence (SI) has proven to be useful in solving issues that are difficult to solve using traditional mathematical methodologies by using a collective behavior of a decentralized or self-organized system. SI-based optimization algorithms use a collaborative trial-and-error process to identify a solution. The development of various efficient swarm optimization methods is largely due to the peer-to-peer learning behavior of social colonies. SI is deeply engaged in the realm of IoT (Internet of Things) and IoT-based systems to control the operations logically. The mounting complexity of IoT devices’ infrastructure framework and continuous communication is lifting undesirable weaknesses with scalability, efficiency, safety, and real-time responses. These vulnerabilities give rise to privacy and security concerns, allowing attackers to potentially exploit them. Intrusion Detection System (IDS) has become a vital aspect of network security for implementing security in IoT devices. So, IDS with SI-supported decentralized algorithms are employed to overcome such difficulties. Since its conception, considerable research has been done to improve the SI-based optimization algorithm’s efficiency and adapt it to various issues. This paper provides an overview of SI advances for IoT-based IDS, applications, comparative performance, and research opportunities in the future for normalizing the IoT processes. The present study delves into the technical aspects of implementing feature selection and parameter tuning within the context of SI. Furthermore, it conducts a comprehensive analysis of SI approaches in the realm of IoT, particularly in conjunction with IDS.