Knowledge Distillation-Based Robust UAV Swarm Communication Under Malicious Attacks

Unmanned aerial vehicle (UAV) swarms have become a promising solution to enhance modern wireless communication in complicated environments. However, due to the existence of real-world malicious attacks, the performance of prediction and optimisation methods used for UAV swarms are easily degraded. In this paper, we propose an efficient and robust knowledge distillation and deep learning-based user mobility prediction, user assignment, and drone position optimisation scheme for UAV swarm-enabled wireless communication systems in the presence of malicious Global Navigation Satellite System (GNSS) spoofing attackers. Specifically, a robust Transformer-based user mobility prediction model is first designed as a teacher model and then distilled into a smaller Gated Recurrent Unit (GRU) student model. Additionally, an efficient user assignment and drone position optimisation method, namely successive differential programming (SDP) is proposed. The proposed deep learning model forecasts user locations, on which we construct and solve assignment and position optimisation problems. Simulation results demonstrate that the optimised sum rate using the distilled GRU student model's predicted user locations can achieve almost 99% compared to the Transformer teacher model. Meanwhile, the inference time of the student model is only 4% compared to the teacher model.