Blockchain-Powered Deep Learning for Internet of Things With Cloud-Assisted Secure Smart Home Networks

Integrating Internet of Things (IoTs) devices with secure smart home networks assisted by the cloud signifies a cutting-edge and potent tool for contemporary home automation. This allows various appliances and devices in a home remotely controlled by the internet to communicate and share data. The typical smart home system depends on the cloud service or centralized server, which makes them further vulnerable to potential security breaches and single points of failure. As a decentralized nature, Blockchain (BC) distributes the control and storage of data across the network, preventing unauthorized attacks. Integrating BC technology into the protected smart home network boosts the system’s dependability, safety, and privacy. In addition, machine learning (ML) and analytics offer behaviour analysis and predictive maintenance for optimized energy consumption. Finally, combining IoT with cloud-assisted security transforms homes into smart, connected ecosystems, offering convenience without integrating confidentiality or dependability. Accordingly, this study presents a BC-based Deep Learning in the Secure Smart Home Network (BPDL-SSHN) methodology in the IoT-cloud platform. In the BPDL-SSHN methodology, BC technology permits secret proficient data from the smart home network. Furthermore, the BPDL-SSHN method follows a series of processes to detect malicious activities such as Binary Fox Optimization Algorithm (BFOA) based feature selection, Attention-based Long Short-Term Memory (ALSTM)-based classification, and Harbor Seal Whiskers Optimization (HSWO)-based hyperparameter tuning. The HSWO method’s design helps better the hyperparameter choice of the ALSTM method, significantly enhancing the recognition performance. The comparative outcome of the BPDL-SSHN methodology reported the proficient solution of the smart home network to detect and monitor malicious or harmful activities. The experimental outcome implied that the BPDL-SSHN methodology accomplishes a maximum accuracy performance of 98.91% over other approaches.