Enhancing PLS in UAV-Aided Backscatter Networks: A Multiagent DRL Framework with Federated Learning

Abstract

In recent years, enhancing physical layer security (PLS) in UAV-aided backscatter networks has received huge attention among the research community due to its various applications, such as smart farming, cognitive healthcare, and intelligent industrial automation, among others. It results in secure and reliable data transmission over the network. In this context, this article proposes a novel federated learning (FL)-enabled multiagent deep reinforcement learning (DRL) framework to enhance the PLS of unmanned aerial vehicle (UAV) -aided backscatter communication networks. We consider a system comprising a UAV assisting a passive backscatter tag (BT) in the presence of a potential eavesdropper (EV). To protect the backscattered information from interception, artificial noise (AN) is injected by the UAV. The objective is to maximize the secrecy rate by jointly optimizing the UAV’s hovering position, power allocation factor, and the BT’s reflection coefficient. To tackle this challenging optimization task, we employ a multiagent DRL approach in which dedicated agents collaboratively learn optimal policies for each parameter. Furthermore, to ensure privacy and improve training efficiency, we integrate an FL scheme where the agents share model updates instead of raw data. Experimental results validate that the proposed framework significantly enhances secrecy performance while enabling decentralized and privacy-preserving learning in UAV-assisted backscatter networks. The results are also compared with other existing methods and varying parameters value, which validate the significance of the utilization of the proposed method.