Aerial Secure Collaborative Communications under Eavesdropper Collusion in Low-altitude Economy: A Generative Swarm Intelligent Approach

TL;DR

This work tackles secure two-way AAV-to-AAV communications under eavesdropper collusion in the LAE by using distributed collaborative beamforming (DCB) and a novel generative swarm intelligence framework (GenSI). It formulates a multi-objective NP-hard problem balancing the minimum two-way known secrecy capacity $C_{KE}$, maximum sidelobe level $f_{SLL}$, and AAV energy cost, and solves it via a CVAE-guided initialization plus MOALO-based evolution. The GenSI approach outperforms state-of-the-art baselines, achieving similar or better optimization with substantially fewer iterations, and the CVAE-based warm start reduces execution time by about 58.7%. Practical analysis shows favorable performance at 915 MHz with robust behavior under phase, CSI, and jitter imperfections, suggesting viability for real-time, resource-constrained AAV deployments in LAE.

Abstract

In this work, we aim to introduce distributed collaborative beamforming (DCB) into AAV swarms and handle the eavesdropper collusion by controlling the corresponding signal distributions. Specifically, we consider a two-way DCB-enabled aerial communication between two AAV swarms and construct these swarms as two AAV virtual antenna arrays. Then, we minimize the two-way known secrecy capacity and maximum sidelobe level to avoid information leakage from the known and unknown eavesdroppers, respectively. Simultaneously, we also minimize the energy consumption of AAVs when constructing virtual antenna arrays. Due to the conflicting relationships between secure performance and energy efficiency, we consider these objectives by formulating a multi-objective optimization problem, which is NP-hard and with a large number of decision variables. Accordingly, we design a novel generative swarm intelligence (GenSI) framework to solve the problem with less overhead, which contains a conditional variational autoencoder (CVAE)-based generative method and a proposed powerful swarm intelligence algorithm. In this framework, CVAE can collect expert solutions obtained by the swarm intelligence algorithm in other environment states to explore characteristics and patterns, thereby directly generating high-quality initial solutions in new environment factors for the swarm intelligence algorithm to search solution space efficiently. Simulation results show that the proposed swarm intelligence algorithm outperforms other state-of-the-art baseline algorithms, and the GenSI can achieve similar optimization results by using far fewer iterations than the ordinary swarm intelligence algorithm. Experimental tests demonstrate that introducing the CVAE mechanism achieves a 58.7% reduction in execution time, which enables the deployment of GenSI even on AAV platforms with limited computing power.

Figures (9)

• Figure 1: A two-way DCB-enabled aerial communication system under the known and unknown eavesdropper collusion in LAE scenarios.
• Figure 2: The structure of the GenSI framework.
• Figure 3: Antenna gains obtained by our proposed GenSI framework. (a) Antenna gain of AVAA1 in cold start case. (b) Antenna gain of AVAA2 in cold start case. (c) Antenna gain of AVAA1 in warm start case. (d) Antenna gain of AVAA2 in warm start case.
• Figure 4: Trajectories of the AAV swarms obtained by our proposed GenSI framework.
• Figure 5: Training loss curves of GenSI framework under different learning rates, where learning rate (i.e., lr) of 0.0005 achieves the optimal convergence performance.