Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Model-Driven Learning-Based Physical Layer Authentication for Mobile Wi-Fi Devices

Yijia Guo, Junqing Zhang, Yao-Win Peter Hong, Stefano Tomasin

Abstract

The rise of wireless technologies has made the Internet of Things (IoT) ubiquitous, but the broadcast nature of wireless communications exposes IoT to authentication risks. Physical layer authentication (PLA) offers a promising solution by leveraging unique characteristics of wireless channels. As a common approach in PLA, hypothesis testing yields a theoretically optimal Neyman-Pearson (NP) detector, but its reliance on channel statistics limits its practicality in real-world scenarios. In contrast, deep learning-based PLA approaches are practical but tend to be not optimal. To address these challenges, we proposed a learning-based PLA scheme driven by hypothesis testing and conducted extensive simulations and experimental evaluations using Wi-Fi. Specifically, we incorporated conditional statistical models into the hypothesis testing framework to derive a theoretically optimal NP detector. Building on this, we developed LiteNP-Net, a lightweight neural network driven by the NP detector. Simulation results demonstrated that LiteNP-Net could approach the performance of the NP detector even without prior knowledge of the channel statistics. To further assess its effectiveness in practical environments, we deployed an experimental testbed using Wi-Fi IoT development kits in various real-world scenarios. Experimental results demonstrated that the LiteNP-Net outperformed the conventional correlation-based method as well as state-of-the-art Siamese-based methods.

Model-Driven Learning-Based Physical Layer Authentication for Mobile Wi-Fi Devices

Abstract

The rise of wireless technologies has made the Internet of Things (IoT) ubiquitous, but the broadcast nature of wireless communications exposes IoT to authentication risks. Physical layer authentication (PLA) offers a promising solution by leveraging unique characteristics of wireless channels. As a common approach in PLA, hypothesis testing yields a theoretically optimal Neyman-Pearson (NP) detector, but its reliance on channel statistics limits its practicality in real-world scenarios. In contrast, deep learning-based PLA approaches are practical but tend to be not optimal. To address these challenges, we proposed a learning-based PLA scheme driven by hypothesis testing and conducted extensive simulations and experimental evaluations using Wi-Fi. Specifically, we incorporated conditional statistical models into the hypothesis testing framework to derive a theoretically optimal NP detector. Building on this, we developed LiteNP-Net, a lightweight neural network driven by the NP detector. Simulation results demonstrated that LiteNP-Net could approach the performance of the NP detector even without prior knowledge of the channel statistics. To further assess its effectiveness in practical environments, we deployed an experimental testbed using Wi-Fi IoT development kits in various real-world scenarios. Experimental results demonstrated that the LiteNP-Net outperformed the conventional correlation-based method as well as state-of-the-art Siamese-based methods.
Paper Structure (43 sections, 1 theorem, 66 equations, 13 figures, 2 tables)

This paper contains 43 sections, 1 theorem, 66 equations, 13 figures, 2 tables.

Table of Contents

  1. Introduction
  2. System Model and Problem Statement
  3. System Model
  4. Problem Statement
  5. Channel Model
  6. Hypothesis Testing
  7. NP Detection
  8. Limitation of Hypothesis Testing
  9. LiteNP-Net, NP Detector-driven Neural Network-based PLA Design
  10. Motivation of LiteNP-Net
  11. LiteNP-Net Design
  12. Design Principles
  13. Design Details
  14. The Proposed LiteNP-Net PLA System
  15. Dataset
  16. ...and 28 more sections

Key Result

Lemma 1

Given the channel estimation model in eq:lsEstimation_vector, the posterior distribution of $\bm{H}_{\rm{ba}}^{[k]}$ given its measurement $\widehat{\bm{H}}_{\rm{ba}}^{[k]}$ can be expressed as where

Figures (13)

  • Figure 1: The system model for PLA in a mobile scenario. Multipath varies due to Bob's movement.
  • Figure 2: The structure of LiteNP-Net.
  • Figure 3: (a) The embedding network $\Psi_{\rm A}$. (b) The embedding networks $\Psi_{\rm B}$ and $\Psi_{\rm C}$.
  • Figure 4: The proposed LiteNP-Net PLA system.
  • Figure 5: The AUC versus $\Delta t_{k}$ on the simulation test dataset with WLAN TGn channel model F, $\text{SNR}=6$ dB, $d_{\rm bm}/\lambda=0.25$ and $v_0=1$ m/s.
  • ...and 8 more figures

Theorems & Definitions (4)

  • proof
  • Lemma 1
  • proof
  • proof