Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Sivaram Krishnan, Jihong Park, Gregory Sherman, Benjamin Campbell, Jinho Choi

TL;DR

A novel framework termed predictive covert communication, aimed at minimizing detectability in terrestrial ad-hoc networks under multi-UAV surveillance, is introduced, showing promise in enabling low-latency covert operations in practical scenarios.

Abstract

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.

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

TL;DR

A novel framework termed predictive covert communication, aimed at minimizing detectability in terrestrial ad-hoc networks under multi-UAV surveillance, is introduced, showing promise in enabling low-latency covert operations in practical scenarios.

Abstract

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.
Paper Structure (28 sections, 23 equations, 7 figures, 4 tables, 2 algorithms)

This paper contains 28 sections, 23 equations, 7 figures, 4 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. System Model and Problem formulation
  3. UAV Surveillance Network
  4. Terrestrial Ad-hoc Network
  5. Power Control Problem for Covert Operations
  6. Existing Methods for Predicting Trajectories of UAV
  7. Single UAV
  8. Multiple UAVs
  9. GKAE and Its Application to Predictive Covert Communication
  10. Graph Neural Network
  11. Koopman AutoEncoder
  12. The Proposed Framework: GKAE for Multi-UAV
  13. Training
  14. Simulation Parameters
  15. Multi-UAV Trajectory Data
  16. ...and 13 more sections

Figures (7)

  • Figure 1: Schematic representation of the proposed predictive covert communication framework, illustrating proactive transmit power assignment to ground nodes by a central unit that predicts long-term trajectories for the multi-UAV network using historical location data.
  • Figure 2: A schematic graph representation is employed for a multi-UAV network, utilizing node feature and adjacency matrices, where UAVs within 100 meters are connected.
  • Figure 3: An illustration of the proposed architecture: Graph-based Koopman Autoencoder (GKAE).
  • Figure 4: Disparity in predicted location versus true location can lead to detection. Downscaling the transmit power helps in preventing detection events.
  • Figure 5: Performance evaluation of the proposed model, including training loss curves and prediction error comparisons.
  • ...and 2 more figures