Deep Graph Reinforcement Learning for UAV-Enabled Multi-User Secure Communications

2025-04-02

AI Summary

In UAV-supported multi-user wireless communications, the high mobility of UAVs poses significant challenges in jointly optimizing physical-layer security and UAV deployment. Method: This paper proposes a deep graph reinforcement learning framework that, for the first time, formulates secure beamforming as a graph neural network (GNN) learning task. It tightly couples GNN message-passing mechanisms with the soft actor-critic (SAC) algorithm to achieve cross-scale joint optimization of 3D UAV placement and secure beamforming. Contribution/Results: The approach substantially improves policy computation efficiency, closely approaches the theoretical optimal secure rate, scales effectively to large dynamic networks, and demonstrates strong robustness and generalization across diverse UAV communication scenarios—including varying user densities, channel dynamics, and interference conditions—without requiring explicit channel state information retraining.

Technology Category

• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Security and Privacy: Large-scale security measurements
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

While unmanned aerial vehicles (UAVs) with flexible mobility are envisioned to enhance physical layer security in wireless communications, the efficient security design that adapts to such high network dynamics is rather challenging. The conventional approaches extended from optimization perspectives are usually quite involved, especially when jointly considering factors in different scales such as deployment and transmission in UAV-related scenarios. In this paper, we address the UAV-enabled multi-user secure communications by proposing a deep graph reinforcement learning framework. Specifically, we reinterpret the security beamforming as a graph neural network (GNN) learning task, where mutual interference among users is managed through the message-passing mechanism. Then, the UAV deployment is obtained through soft actor-critic reinforcement learning, where the GNN-based security beamforming is exploited to guide the deployment strategy update. Simulation results demonstrate that the proposed approach achieves near-optimal security performance and significantly enhances the efficiency of strategy determination. Moreover, the deep graph reinforcement learning framework offers a scalable solution, adaptable to various network scenarios and configurations, establishing a robust basis for information security in UAV-enabled communications.

Problem

• UAV-enabled secure communications under high network dynamics
• Joint optimization of UAV deployment and transmission security
• Scalable security solution for multi-user interference management

Innovation

• Deep graph reinforcement learning framework
• GNN-managed security beamforming
• Soft actor-critic guided UAV deployment