Research On Secure And Trustworthy Internet Of Things Based On Edge Intelligence

With the wide utilization of intelligent mobile devices in the fifthgeneration(5G)era and the advances in wireless communication techniques in the forthcoming sixth-generation(6G)communication systems,the Internet of Things(IoT)is increasingly attracting attentions from both academia and industry as a versatile technology.Nowadays,more and more intelligent devices get access to IoT networks,where each object with identifying,sensing,networking,and processing capabilities can communicate with other nodes.To ensure long-term,secure and stable operations of IoT networks,novel technical schemes for IoT data security and device security are designed.Specifically,the following two aspects of IoT security and trustworthy technology research are developed:1)A mobile edge computing(MEC)-enabled blockchain system is proposed in this study for secure and efficient data storage and sharing in IoT networks,with the MEC acting as an overlay system to provide dynamic computation offloading services.Considering latency-critical,resource-limited and dynamic IoT scenarios,an adaptive system resource allocation and computation offloading scheme is designed to optimize the scalability performance for MEC-enabled blockchain systems,wherein the scalability is quantified as MEC computational efficiency and blockchain system throughput.Specifically,computation offloading policy and block generation strategy are jointly considered to maximize the scalability of MEC-enabled blockchain systems,and meanwhile guarantee data security and system efficiency.In contrast to existing works that ignore frequent user movement and dynamic task requirements in IoT networks,the joint performance optimization scheme is formulated as a Markov decision process(MDP).Furthermore,a deep deterministic policy gradient(DDPG)-based algorithm is proposed to solve the MDP problem on each IoT node.Specifically,DDPG can solve an MDP problem with a continuous action space and it only requires a straightforward actor-critic architecture,making it suitable for tackling the dynamics and complexity of the MEC-enabled blockchain system.As demonstrated by simulations,the proposed scheme can achieve performance improvements over the deep Q network(DQN)based and some other greedy schemes in terms of longterm transactional throughput.2)A federated learning-based device anomaly detection scheme is proposed and a heterogeneity-aware federated optimization algorithm(Clustered-FedProx)is designed.With the popularity and application of Industrial Internet of Things(IIoT),device anomaly detection is considered as one of the important challenges in IIoT implementation.However,the privacy sensitivity of device data and the highly heterogeneity of IIoT devices make it impossible for traditional schemes to achieve efficient,accurate,and privacy-protected device anomaly detection in IIoT networks.Considering the privacy and heterogeneity arising from differences in system resources and data statistics among devices in IIoT networks,an optimized federated learning-based approach is presented,whereby multiple devices can be coordinated to train a global deep learning model in highly heterogeneous networks.Our proposed scheme is lightweight and suitable for online device anomaly detection.Simulation results show that the proposed scheme can achieve more stable and accurate performance than conventional schemes.Finally,a summary of the research content and an outlook on challenges such as blockchain security and federated learning security are given.