A Joint Learning and Communication Framework for Intrusion Detection in Wireless Networks with High-Speed UAVs

Qiqi Yu, Junhua Wu, Xin Fan, Xiaoshan Cui, Tielin Wang, Guangshun Li, Chuanwen Luo

Abstract: The problem of training federated learning(FL) algorithms which is used to perform intrusion detection and protect data privacy in actual wireless networks is studied. Specifically, unmanned aerial vehicles(UAVs) can move at high speeds that results the doppler effect, which further deteriorates the communicational quality of the wireless network interactions with the base station. Since all training parameters are transmitted through the wireless network, the quality of training is affected by many factors such as packet errors and the number of wireless resources. The federated learning and wireless communication is formulated as an optimization problem, whose goal is to minimize the FL loss function that captures the performance of the algorithm. To solve the problems, we present the PVBO: transmit power, velocity and resource block allocation joint optimization algorithm. Based on the expected convergence rate of the FL algorithm, the optimal transmit power and velocity for each UAV are derived, under a given uplink resource block allocation scheme. Then, the uplink resource block allocation is optimized so as to minimize the FL loss function. The simulation results show that it can averagely improve the accuracy of intrusion detection by 4.53\(\%\) compared to the randomized policy.

External IDs:dblp:conf/wasa/YuWFCWLL25