Cooperative Covert Communication and Task Offloading for AI-Empowered Multi-UAV Networks

Abstract

Multi-UAV edge networks, as an effective supplement to ground sensor systems, can significantly improve perception coverage and data processing efficiency. However, as UAV networks scale up, effective multi-UAV cooperation becomes increasingly critical and challenging, especially for coupled deployment, task allocation, and resource management. Meanwhile, due to the openness and broadcast nature of wireless channels, UAV transmissions are vulnerable to eavesdropping, making cooperative security protection essential for reliable UAV edge computing. To address these issues, this paper investigates a multi-UAV secure edge computing scenario in which UAVs cooperate both for self-jamming to thwart the aerial eavesdropper and for distributed edge computing to assist task processing. We establish the digital models of the UAV secure edge computing workflow and formulate the latency minimization problem under covert communication constraints. Then, a particle swarm optimization (PSO) + block coordinate descent (BCD) method for discrete state spaces and a multi-agent deep deterministic policy gradient (MADDPG)-based scheme suitable for continuous real-world environments are proposed, respectively. Extensive analysis and simulations demonstrate the effectiveness of our methods, achieving covert task offloading while significantly reducing task processing latency.