Predictive Covert Communication Against Multi-UAV Surveillance Using Graph Koopman Autoencoder

被引:0
作者
Krishnan, Sivaram [1 ]
Park, Jihong [1 ,2 ]
Sherman, Gregory [3 ]
Campbell, Benjamin [3 ]
Choi, Jinho
机构
[1] Univ Adelaide, Sch Elect & Mech Engn, Adelaide, SA 5005, Australia
[2] Singapore Univ Technol & Design, Informat Syst Technol & Design Pillar, Singapore 487372, Singapore
[3] Def Sci & Technol Grp, Platforms Div, Mission Auton, Canberra, ACT 2610, Australia
关键词
Ad hoc networks; Autonomous aerial vehicles; Surveillance; Trajectory; Wireless communication; Vehicle dynamics; Graph neural networks; Autoencoders; Signal to noise ratio; Wireless sensor networks; Covert communication; graph neural network; Koopman operator theory; low probability of detection communication; prediction of dynamical systems; wireless ad-hoc network; SYSTEMS; APPROXIMATION;
D O I
10.1109/TVT.2025.3537578
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Low Probability of Detection (LPD) communication aims to obscure the presence of radio frequency (RF) signals to evade surveillance. In the context of mobile surveillance utilizing unmanned aerial vehicles (UAVs), achieving LPD communication presents significant challenges due to the UAVs' rapid and continuous movements, which are characterized by unknown nonlinear dynamics. Therefore, accurately predicting future locations of UAVs is essential for enabling real-time LPD communication. In this paper, we introduce a novel framework termed predictive covert communication, aimed at minimizing detectability in terrestrial ad-hoc networks under multi-UAV surveillance. Our data-driven method synergistically integrates graph neural networks (GNN) with Koopman theory to model the complex interactions within a multi-UAV network and facilitating long-term predictions by linearizing the dynamics, even with limited historical data. Extensive simulation results substantiate that the predicted trajectories using our method result in at least 63%-75% lower probability of detection when compared to well-known state-of-the-art baseline approaches, showing promise in enabling low-latency covert operations in practical scenarios.
引用
收藏
页码:9165 / 9179
页数:15
相关论文
共 66 条
[1]  
Azencot O, 2020, PR MACH LEARN RES, V119
[2]   Hiding Information in Noise: Fundamental Limits of Covert Wireless Communication [J].
Bash, Boulat A. ;
Goeckel, Dennis ;
Towsley, Don ;
Guha, Saikat .
IEEE COMMUNICATIONS MAGAZINE, 2015, 53 (12) :26-+
[3]   LEARNING LONG-TERM DEPENDENCIES WITH GRADIENT DESCENT IS DIFFICULT [J].
BENGIO, Y ;
SIMARD, P ;
FRASCONI, P .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (02) :157-166
[4]  
Sorbelli FB, 2024, ACM Journal on Autonomous Transportation Systems, V1, P1, DOI [10.1145/3649224, https://doi.org/10.1145/3649224, DOI 10.1145/3649224]
[5]   Efficient Immersive Surveillance of Inaccessible Regions using UAV Network [J].
Bist, Anuj ;
Singhal, Chetna .
IEEE CONFERENCE ON COMPUTER COMMUNICATIONS WORKSHOPS (IEEE INFOCOM WKSHPS 2021), 2021,
[6]   Modern Koopman Theory for Dynamical Systems [J].
Brunton, Steven L. ;
Budisic, Marko ;
Kaiser, Eurika ;
Kutz, J. Nathan .
SIAM REVIEW, 2022, 64 (02) :229-340
[7]  
Brunton SL, 2019, DATA-DRIVEN SCIENCE AND ENGINEERING: MACHINE LEARNING, DYNAMICAL SYSTEMS, AND CONTROL, P117
[8]   Discovering governing equations from data by sparse identification of nonlinear dynamical systems [J].
Brunton, Steven L. ;
Proctor, Joshua L. ;
Kutz, J. Nathan .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2016, 113 (15) :3932-3937
[9]   Koopman Invariant Subspaces and Finite Linear Representations of Nonlinear Dynamical Systems for Control [J].
Brunton, Steven L. ;
Brunton, Bingni W. ;
Proctor, Joshua L. ;
Kutz, J. Nathan .
PLOS ONE, 2016, 11 (02)
[10]  
Buterez D, 2022, ADV NEUR IN