Hybrid Deep Neural Network Model for Detection of Security Attacks in IoT Enabled Environment

The extensive use of Internet Things (IoT) appliances has greatly contributed in the growth smart cities. Moreover, city deploys IoT-enabled applications, communications, and technologies to improve quality life, people’s wellbeing, services for service providers increase operational efficiency. Nevertheless, expansion network become utmost hazard due increased cyber security attacks threats. Consequently, it is more significant develop system models preventing also protect IoT devices from hazards. This paper aims present a novel deep hybrid attack detection method. input data subjected preprocessing phase. Here, normalization process carried out. From preprocessed data, statistical higher order features are extracted. Finally, extracted learning model detecting presence attack. proposed classifier combines like Convolution Neural Network (CNN) Deep Belief (DBN). To make precise accurate, training CNN DBN out by using Seagull Adopted Elephant Herding optimization (SAEHO) tuning optimal weights.