Distributed Federated Learning-Based AIOT Framework for Secure High Speed Communication Network

The grouping of artificial intelligence with the Internet of Things (IoT) can enhance the user experience in IoT applications. In the IoT, information sharing can improve the quality of applications, however, it also introduces problems with data security, like data leakage and the inability to confirm data as it is being shared in a high-speed communication network. In this paper combining distributed federated learning, blockchain technology, and encryption verification, the study suggests a strategy for ensuring the authenticity and confidentiality of data transmitted over high-speed communication Networks in the Internet of Things (IoT). At first, the usage of united learning and blockchain innovation is utilized to change over the immediate trade of crude information inside the IoT into the trading of encoded model boundaries. Then, at that point, to check and pick the chain’s boundaries during the model accumulation stage, an encryption confirmation approach is recommended. As a last step, we contrast the proposed strategy with others. Experimental results show that the proposed method can effectively ensure data privacy and enable the verification of encrypted data, guaranteeing the accuracy of the final model and providing a safeguard for high-quality data sharing in the IoT over high-speed communication network.