Blockchain-driven cybersecurity detection model using quantum bidirectional gated recurrent unit with metaheuristic algorithms on IoT environment

The fast development of the Internet of Things (IoT) has led to a rising number of interrelated devices, creating novel chances for data automation and collection. This growth also presents unique cybersecurity threats. In IoT devices, cyberattacks can result in serious consequences such as unauthorized access, data breaches, and disruption of critical services. Thus, numerous research surveys have concentrated on the design of intrusion detection systems (IDS). Furthermore, blockchain (BC) technology is implemented to enhance security. BC delivers a robust device for securing data and transactions of IoT systems. By leveraging BC's technology, IoT systems benefit from improved privacy and security. In this study, I proposed a Blockchain Driven Cybersecurity Detection Using Metaheuristic Optimization Algorithms and a Deep Learning Model (BCCD-MOADLM). My main intention of the BCCD-MOADLM model was to detect and classify cybersecurity in an IoT environment using advanced optimization models. BC has emerged as a promising solution for improving the privacy and security of IoT networks. Furthermore, the data pre-processing stage applied z-score normalization to transform input data into a compatible format. The Osprey optimization algorithm (OOA) technique was employed for the dimensionality reduction. Moreover, the quantum bidirectional gated recurrent unit (QBiGRU) technique was used for cybersecurity classification. The parameter selection for QBiGRU was performed using the Pelican optimizer algorithm (POA) technique. The experimental evaluation of the BCCD-MOADLM approach was examined under the BoT-IoT dataset. The comparison outcomes of the BCCD-MOADLM approach portrayed a superior accuracy value of 99.32% over existing models.