Secrecy Outage Performance of Ground-to-Air Communications With Multiple Aerial Eavesdroppers and Its Deep Learning Evaluation

In this letter, we study the secure information transmission from a ground base station (GBS) to a legitimate unmanned aerial vehicle (UAV) user, in the presence of multiple UAV eavesdroppers. To enhance the secrecy performance, the GBS applies beamforming transmission while enforcing a protection zone around it. Utilizing the general kappa-mu shadowed fading distribution to model the ground-to-air channel, we derive an exact expression of the secrecy outage probability (SOP). To further facilitate performance evaluation, we adopt a data-driven approach and develop a deep learning model that can predict the SOP performance with high accuracy and short computation time. Through selected numerical results, we examine the effect of different system parameters on the SOP performance.