Soft computing in secure social internet of things based on post-quantum blockchain with federated learning

Abstract

A system's compliance with a specified security model, security standard, or specification is the focus of a security evaluation. The process of selecting the appropriate model for security assessment is determined by the type of cryptosystem. There are various models available. By enhancing data authentication and security for soft computing, this study proposes a novel technique for secure social internet of things (SSIoT) privacy analytics using post-quantum blockchain federated learning with encryption and trust analysis, the privacy analysis and data authentication. In terms of latency, QoS, energy consumption, packet loss rate, and other parameters, the experimental analysis is carried out. The purpose of the security analysis and performance evaluations is to demonstrate that the proposed scheme can satisfy the security requirements and enhance the FL model's performance. Federated learning is able to carry out effective machine learning (ML) with multiple participants while maintaining privacy of terminal personal data. Our proposed combination of federated learning as well as blockchain provides a solid foundation for future industrial Internet, as demonstrated by the numerical results.the proposed technique attainedenergy consumption of 55%, packet loss rate of 59%, QoS of 79%, Latency of 72%, network security analysis of 82%.