Enhanced Metaheuristics with Deep Learning Model for Blockchain Assisted Cyber Security Solution in Internet of Things Environment

Internet of Things (loT) devices can be extensively utilized by several industries containing smart farming, smart logistics, smart medicine, smart cities, and so on. But, Distributed Denial of Service (DDoS) outbreaks position is a critical attack to IoT safety. Attackers simply employ the vulnerabilities of IoT devices and they control a portion of botnets to introduce DDoS attacks. IoT devices can be limited resources with restricted memory and calculating resources. While a developing technology, Blockchain (BC) has a great to resolving the security problems from the IoT. As a result, it can be essential to analyze distinct BC-based solutions for mitigating DDoS attacks from the IoT. This study develops Enhanced Metaheuristics with Deep Learning Model for BC Assisted Cybersecurity Solution (EMDLM-BCCS) technique in IoT platform. To allow secure data transmission from the IoT networks, BC technology can be applied. The EMDLM-BCCS algorithm follows initial stage of data pre-processing to normalize the input data. For attack detection, the EMDLM-BCCS approach makes use of extreme learning machine (ELM) approach. To enhance the detection results of the ELM model, elite-oppositional grasshopper optimization algorithm (EGOA) can be utilized. The simulated value of the EMDLM-BCCS approach can be validated on BoT-IoT dataset. The obtained values infer the better solution of the EMDLM-BCCS algorithm in terms of different measures.