| Abstract |
The use of drone technology and drones are currently widespread due to their increasing applications. However, there are some specific security-based challenges in the authentication process. In most drone-based applications, there are many authentication approaches, which are subject to handover delay issues with security complexities for an attack. To end these issues, the presented research has focused on developing a novel Optimized deep learning model known as Fruit Fly based UNet Drone Assisted Security (FFUDAS) to remove the malicious attacks. Moreover, the user requests are stored in the cloud, and the stored data are trained to the drones. Hereafter, the drones can deliver medicine to the requestor's location; in that, the malicious attacks were changes the location of drones. Once the attack is identified, then the attack removal process is done. Finally, the new path location to the requested user was identified with the help of fruit fly fitness; then the medicines are delivered to the requested user's location. Furthermore, the designed procedure is executed in an NS2 platform with required nodes. The robustness of the presented model was verified by evaluating the metrics like confidential data rate, execution time, handover delay, pack perception and data delivery rate, and energy consumption. Furthermore, to identify the effectiveness of the presented work, the presented model is compared with other existing schemes. The comparison results show that the presented model has higher throughput, less execution time and handover delay. |
