Scalable Intrusion Detection in IoT: An Optimized Deep Belief Network Framework

Abstract

The Internet of Things (IoT) is a cutting-edge technology that was created with the goal of connecting and integrating all items globally. This technology makes it possible to be incredibly intelligent, which benefits humans in many ways. Connecting the things around us and enabling communication between them will enable applications for intelligent healthcare, safety, and industrial operations. Due to the multiplicity of different organisations and applications that the Internet of Things supports, the risk of unwanted access is substantially larger. The communication networks are currently subject to very potent and seriously frightening cyberattacks. This research introduces an intelligent strategy using improved Deep Learning algorithms to enhance security and resist breaches. The study focuses on detecting active hostile behavior within networks, employing Deep Learning for intrusion detection. The enhanced Deep Belief Network (DBN) for security is compared with traditional algorithms, including DGAs and IDS, to analyze outcomes.