Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Securing the Skies: An IRS-Assisted AoI-Aware Secure Multi-UAV System with Efficient Task Offloading

Poorvi Joshi, Alakesh Kalita, Mohan Gurusamy

TL;DR

This work addresses securing timely information in IRS-assisted UAV networks by integrating AoI-aware optimization with physical-layer security. It proposes a bi-layer UAV architecture (C-UAVs and I-UAVs) supported by Intelligent Reflecting Surfaces and a transformer-enhanced multi-agent DRL (GTr-DRL) to jointly optimize task offloading, UAV trajectories, and IRS beamforming. The framework introduces exponential AoI penalty metrics and secrecy-rate maximization under energy and mobility constraints, formulated as a decentralized MDP and solved via DTCE and V-trace-based training. Results show improved AoI performance and secrecy rates compared to baselines, revealing a trade-off: increasing network elements enhances security but can reduce average secrecy due to more unknown channels, emphasizing the need to balance AoI and confidentiality in practical deployments.

Abstract

Unmanned Aerial Vehicles (UAVs) are integral in various sectors like agriculture, surveillance, and logistics, driven by advancements in 5G. However, existing research lacks a comprehensive approach addressing both data freshness and security concerns. In this paper, we address the intricate challenges of data freshness, and security, especially in the context of eavesdropping and jamming in modern UAV networks. Our framework incorporates exponential AoI metrics and emphasizes secrecy rate to tackle eavesdropping and jamming threats. We introduce a transformer-enhanced Deep Reinforcement Learning (DRL) approach to optimize task offloading processes. Comparative analysis with existing algorithms showcases the superiority of our scheme, indicating its promising advancements in UAV network management.

Securing the Skies: An IRS-Assisted AoI-Aware Secure Multi-UAV System with Efficient Task Offloading

TL;DR

This work addresses securing timely information in IRS-assisted UAV networks by integrating AoI-aware optimization with physical-layer security. It proposes a bi-layer UAV architecture (C-UAVs and I-UAVs) supported by Intelligent Reflecting Surfaces and a transformer-enhanced multi-agent DRL (GTr-DRL) to jointly optimize task offloading, UAV trajectories, and IRS beamforming. The framework introduces exponential AoI penalty metrics and secrecy-rate maximization under energy and mobility constraints, formulated as a decentralized MDP and solved via DTCE and V-trace-based training. Results show improved AoI performance and secrecy rates compared to baselines, revealing a trade-off: increasing network elements enhances security but can reduce average secrecy due to more unknown channels, emphasizing the need to balance AoI and confidentiality in practical deployments.

Abstract

Unmanned Aerial Vehicles (UAVs) are integral in various sectors like agriculture, surveillance, and logistics, driven by advancements in 5G. However, existing research lacks a comprehensive approach addressing both data freshness and security concerns. In this paper, we address the intricate challenges of data freshness, and security, especially in the context of eavesdropping and jamming in modern UAV networks. Our framework incorporates exponential AoI metrics and emphasizes secrecy rate to tackle eavesdropping and jamming threats. We introduce a transformer-enhanced Deep Reinforcement Learning (DRL) approach to optimize task offloading processes. Comparative analysis with existing algorithms showcases the superiority of our scheme, indicating its promising advancements in UAV network management.
Paper Structure (17 sections, 14 equations, 5 figures, 2 algorithms)

This paper contains 17 sections, 14 equations, 5 figures, 2 algorithms.

Table of Contents

  1. Introduction
  2. System and Channel Model
  3. Transmission Protocol
  4. Task Offloading Protocol
  5. Transmission from UE to C-UAV (U2C)
  6. Computation at C-UAV
  7. Transmission from C-UAV to BS via I-UAV (C2I)
  8. Computation at BS
  9. UAV movement
  10. Problem Formulation and Transformation
  11. Problem Statement
  12. Markov Decision Problem (MDP) Formulation
  13. GTr-DRL Algorithm
  14. Transformer-Enhanced Distributed Framework
  15. Optimization
  16. ...and 2 more sections

Figures (5)

  • Figure 1: The system model of proposed UAV network
  • Figure 2: Proposed Solution Network
  • Figure 3: C-UAV Trajectory and Task Allocation
  • Figure 4: Performance parameters vs number of C-UAVs
  • Figure 5: Performance parameters vs number of I-UAVs