Anomaly detection and trust authority in artificial intelligence and cloud computing

The rapid development of smart Internet of Things (IoT) and its multimedia applications with conventional cloud and edge computing platforms are driving a new trend that shifts the functions of centralized networks. These centralized cloud and edge computing networks are encountering various new routing and security challenges. These networks are vulnerable due to different malicious activities and security attacks. The malicious activities lead to link failure and wrong forwarding decisions and or divert the paths. To detect the malicious activities in these networks, we need an efficient detection system for malicious switches in Software Defined Networks (SDN) data plan and leads to data traffic diversion and degrades the network performance. Another aspect is the trust of edge devices and always need to trustworthy devices to forward the IoT devices data to SDN networks. In this paper, we proposed a Software-Defined Network-based Anomaly Detection System (SDN-ADS) for edge computing-based system architecture for IoT networks. Afterwards, we proposed an anomaly detection system to detect the device's behaviour for SDN and edge computing networks. Also, we proposed a Trusted Authority for Edge Computing (TA-Edge) to ensure the trust of edge devices for data forwarding. The edge device is acting as a certificate authority for the specified trusted domain. To overcome the edge devices overhead, in this proposed TA-Edge model, the edge node, only one time, verifies the certificate and when the trust is established, all communication can be done through local certificates. The simulation results show the better performance of proposed systems in terms of different performance parameters