Next-Generation Deep Learning Integrated Drone Security: A 6G-Powered Enabled Edge Cloud Architecture

With the development of wireless communication, such as 6G, the use of drone technologies has been increasing daily. Generally, these drone technologies are connected to remote services, such as edge cloud services, to perform various tasks, including location searching, scheduling, and others. However, the 6G wireless-enabled distributed edge cloud networks paradigm for drone technologies is heavily suffering from security issues. In this paper, we present the next-generation deep learning-integrated security architecture for drone applications based on 6G-enabled edge cloud networks. We present the convolutional neural network-integrated scheduling security (CNN-SS) algorithm methodology for scheduling all drone tasks securely across different drones, 6G wireless networks, and edge cloud nodes. We analysed the security challenges in terms of detection and prevention based on the CNN security scheme, which is trained on the testbed drone security dataset. Simulation results show that CNN-SS achieves efficient scheduling of all drone tasks with minimum end-to-end latency and a higher security validation ratio compared to existing drone security technologies.