When UAV Swarm Meets IRS: Collaborative Secure Communications in Low-altitude Wireless Networks

TL;DR

The paper tackles secure communications in low-altitude wireless networks by integrating UAV swarm-based collaborative beamforming (VAA) with an intelligent reflecting surface (IRS). It models a dynamic, heterogeneous setting and casts the joint UAV trajectory, VAA excitation, and IRS phase-shift design as a multi-objective optimization problem, aiming to maximize secrecy rate while suppressing sidelobes and reducing energy use. A heterogeneous multi-agent DRL framework (HMCA) is proposed, featuring an IRS policy and an enhanced MASAC-based UAV policy with a self-attention critic and gravity-based exploration, enabling coordinated online control. Simulation results show HMCA outperforms baselines across secrecy, sidelobe control, and energy metrics, with better scalability as the number of UAVs increases. The work demonstrates the value of combining mobility, passive beamforming, and deep reinforcement learning for robust, secure, and energy-efficient LAWNs.

Abstract

Low-altitude wireless networks (LAWNs) represent a promising architecture that integrates unmanned aerial vehicles (UAVs) as aerial nodes to provide enhanced coverage, reliability, and throughput for diverse applications. However, these networks face significant security vulnerabilities from both known and potential unknown eavesdroppers, which may threaten data confidentiality and system integrity. To solve this critical issue, we propose a novel secure communication framework for LAWNs where the selected UAVs within a swarm function as a virtual antenna array (VAA), complemented by intelligent reflecting surface (IRS) to create a robust defense against eavesdropping attacks. Specifically, we formulate a multi-objective optimization problem that simultaneously maximizes the secrecy rate while minimizing the maximum sidelobe level and total energy consumption, requiring joint optimization of UAV excitation current weights, flight trajectories, and IRS phase shifts. This problem presents significant difficulties due to the dynamic nature of the system and heterogeneous components. Thus, we first transform the problem into a heterogeneous Markov decision process (MDP). Then, we propose a heterogeneous multi-agent control approach (HMCA) that integrates a dedicated IRS control policy with a multi-agent soft actor-critic framework for UAV control, which enables coordinated operation across heterogeneous network elements. Simulation results show that the proposed HMCA achieves superior performance compared to baseline approaches in terms of secrecy rate improvement, sidelobe suppression, and energy efficiency. Furthermore, we find that the collaborative and passive beamforming synergy between VAA and IRS creates robust security guarantees when the number of UAVs increases.

Figures (7)

• Figure 1: The considered UAV swarm-IRS collaborative secure communication system.
• Figure 2: The proposed HMCA structure with hybrid IRS control policy and MADRL optimization method. The UAV agents based on the MADRL method and the IRS agent based on the IRS control policy.
• Figure 3: Hyperparameter tuning results. (a) Different learning rates. (b) Different discount factors.
• Figure 4: Optimization results obtained by different methods under varying numbers of UAVs. (a) Average secrecy rate. (b) Average total maximum SLL. (c) Total energy consumption obtained by different methods.
• Figure 5: Convergence curve obtained by different methods.