Latency-sensitive covert federated learning via UAV

Federated learning (FL) can preserve data privacy; however, it is limited by the coverage of static edge servers deployed at wireless base stations. Although an unmanned aerial vehicle (UAV) can extend the wireless coverage of FL, it is vulnerable to security risks due to the frequent exchanges of model parameters. Therefore, we propose a UAV-assisted covert FL scheme to protect the transmission of local models from being detected by a warden. The UAV acts as a flying server to collect the local models from distributed ground devices, thereby improving the transmission quality and efficiency. We analyze the error detection probability with an optimal threshold at the warden, which poses a significant security threat to FL. Then, we derive an optimal expression of transmit power at the devices. To minimize the FL latency while satisfying the covertness constraint, the trajectory of UAV can be dynamically adjusted along with the jamming power and the local accuracy, addressing the demands of latency-sensitive applications. Specifically, we propose an iterative algorithm to divide the original problem into two subproblems, which are alternately optimized via successive convex approximation until convergence. Numerical results demonstrate the effectiveness of the proposed UAV-assisted covert FL scheme in minimizing the latency while guaranteeing the covertness.