Archimedes Optimization with Deep Learning Based Aerial Image Classification for Cybersecurity Enabled UAV Networks

Abstract

The recent adoption of satellite technologies, unmanned aerial vehicles (UAVs) and 5G has encouraged telecom networking to evolve into more stable service to remote areas and render higher quality. But, security concerns with drones were increasing as drone nodes have been striking targets for cyberattacks because of immensely weak inbuilt and growing poor security volumes. This study presents an Archimedes Optimization with Deep Learning based Aerial Image Classification and Intrusion Detection (AODL-AICID) technique in secure UAV networks. The presented AODL-AICID technique concentrates on two major processes: image classification and intrusion detection. For aerial image classification, the AODL-AICID technique encompasses MobileNetv2 feature extraction, Archimedes Optimization Algorithm (AOA) based hyperparameter optimizer, and backpropagation neural network (BPNN) based classifier. In addition, the AODL-AICID technique employs a stacked bi-directional long short-term memory (SBLSTM) model to accomplish intrusion detection for cybersecurity in UAV networks. At the final stage, the Nadam optimizer is utilized for parameter tuning of the SBLSTM approach. The experimental validation of the AODL-AICID technique is tested and the obtained values reported the improved performance of the AODL-AICID technique over other models.