Internet of Things (IoT) anomaly detection is significant due to its fundamental roles of securing modern critical infrastructures, such as falsified data injection detection and transmission line faults diagnostic in smart grids. Researchers have proposed various detection methods fostered by machine learning (ML) techniques. Federated learning (FL), as a promising distributed ML paradigm, has been employed recently to improve detection performance due to its advantages of privacy-preserving and lower latency. However, existing FL-based methods still suffer from efficiency, robustness, and security challenges. To address these problems, in this article, we initially introduce a blockchain-empowered decentralized and asynchronous FL framework for anomaly detection in IoT systems, which ensures data integrity and prevents single-point failure while improving the efficiency. Further, we design an improved differentially private FL based on generative adversarial nets, aiming to optimize data utility throughout the training process. To the best of our knowledge, it is the first system to employ a decentralized FL approach with privacy-preserving for IoT anomaly detection. Simulation results on the real-world dataset demonstrate the superior performance from aspects of robustness, accuracy, and fast convergence while maintaining high level of privacy and security protection.

The Internet of Things (IoT) is used in homes and hospitals and deployed outdoors to control and report environmental changes, prevent fires, and perform many more beneficial functions. However, all these benefits come at the tremendous risk of loss of privacy and security issues. To protect the IoT, much research has been carried out to address these risks and find better ways to eliminate them or at least minimize their impact on user privacy and security requirements. This article expounds various network security risks faced by the IoT, analyzes their impacts, discusses risk assessment methods, shows the causes and hazards of these threats, and proposes an overall framework of privacy security protection. This article summarizes the typical defect types in the implementation of IoT firmware, analyzes the generation mechanism of typical defects from the perspectives of fuzzy testing, program verification and machine learning, and compares and expounds the progress of security research for several common IoT protocols. This article analyzes and summarizes the mainstream access control model in the existing IoT and the access control model after using the blockchain and builds a new integrated AIoT architecture for intelligent information processing. Finally, this article expounds on the current legal development status of the privacy protection of network information in various countries and discusses the future prospects of the IoT.

Cloud computing is an emerging technology and it allows users to pay as you need and has the high performance. Cloud computing is a heterogeneous system as well and it holds large amount of application data. In the process of scheduling some intensive data or computing an intensive application, it is acknowledged that optimizing the transferring and processing time is crucial to an application program. In this paper in order to minimize the cost of the processing we formulate a model for task scheduling and propose a particle swarm optimization (PSO) algorithm which is based on small position value rule. By virtue of comparing PSO algorithm with the PSO algorithm embedded in crossover and mutation and in the local research, the experiment results show the PSO algorithm not only converges faster but also runs faster than the other two algorithms in a large scale. The experiment results prove that the PSO algorithm is more suitable to cloud computing.