Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Channel-Robust RFF for Low-Latency 5G Device Identification in SIMO Scenarios

Yingjie Sun, Guyue Li, Hongfu Chou, Aiqun Hu

TL;DR

This work tackles ultra-low-latency device identification in 5G by introducing a channel-robust radio frequency fingerprint (RFF) extraction method for SIMO systems. By leveraging co-temporal CFRs from multiple receive antennas and sub-band LLDR, the approach suppresses multipath distortion without requiring additional signaling, enabling a single uplink transmission. The method delivers high identification accuracy (e.g., $96.13\%$ for $30$ UEs at $20$ dB SNR in a $20$-path channel) and satisfies URLLC latency targets with an air-interface latency of approximately $0.491$ ms. A CNN-based learning pipeline further enables robust UE identification from RFF features. Overall, the proposed framework provides a practical, low-latency solution for secure device identification in dense 5G deployments under realistic multipath conditions.

Abstract

Ultra-low latency, the hallmark of fifth-generation mobile communications (5G), imposes exacting timing demands on identification as well. Current cryptographic solutions introduce additional computational overhead, which results in heightened identification delays. Radio frequency fingerprint (RFF) identifies devices at the physical layer, blocking impersonation attacks while significantly reducing latency. Unfortunately, multipath channels compromise RFF accuracy, and existing channel-resilient methods demand feedback or processing across multiple time points, incurring extra signaling latency. To address this problem, the paper introduces a new RFF extraction technique that employs signals from multiple receiving antennas to address multipath issues without adding latency. Unlike single-domain methods, the Log-Linear Delta Ratio (LLDR) of co-temporal channel frequency responses (CFRs) from multiple antennas is employed to preserve discriminative RFF features, eliminating multi-time sampling and reducing acquisition time. To overcome the challenge of the reliance on minimal channel variation, the frequency band is segmented into sub-bands, and the LLDR is computed within each sub-band individually. Simulation results indicate that the proposed scheme attains a 96.13% identification accuracy for 30 user equipments (UEs) within a 20-path channel under a signal-to-noise ratio (SNR) of 20 dB. Furthermore, we evaluate the theoretical latency using the Roofline model, resulting in the air interface latency of 0.491 ms, which satisfies ultra-reliable and low-latency communications (URLLC) latency requirements.

Channel-Robust RFF for Low-Latency 5G Device Identification in SIMO Scenarios

TL;DR

This work tackles ultra-low-latency device identification in 5G by introducing a channel-robust radio frequency fingerprint (RFF) extraction method for SIMO systems. By leveraging co-temporal CFRs from multiple receive antennas and sub-band LLDR, the approach suppresses multipath distortion without requiring additional signaling, enabling a single uplink transmission. The method delivers high identification accuracy (e.g., for UEs at dB SNR in a -path channel) and satisfies URLLC latency targets with an air-interface latency of approximately ms. A CNN-based learning pipeline further enables robust UE identification from RFF features. Overall, the proposed framework provides a practical, low-latency solution for secure device identification in dense 5G deployments under realistic multipath conditions.

Abstract

Ultra-low latency, the hallmark of fifth-generation mobile communications (5G), imposes exacting timing demands on identification as well. Current cryptographic solutions introduce additional computational overhead, which results in heightened identification delays. Radio frequency fingerprint (RFF) identifies devices at the physical layer, blocking impersonation attacks while significantly reducing latency. Unfortunately, multipath channels compromise RFF accuracy, and existing channel-resilient methods demand feedback or processing across multiple time points, incurring extra signaling latency. To address this problem, the paper introduces a new RFF extraction technique that employs signals from multiple receiving antennas to address multipath issues without adding latency. Unlike single-domain methods, the Log-Linear Delta Ratio (LLDR) of co-temporal channel frequency responses (CFRs) from multiple antennas is employed to preserve discriminative RFF features, eliminating multi-time sampling and reducing acquisition time. To overcome the challenge of the reliance on minimal channel variation, the frequency band is segmented into sub-bands, and the LLDR is computed within each sub-band individually. Simulation results indicate that the proposed scheme attains a 96.13% identification accuracy for 30 user equipments (UEs) within a 20-path channel under a signal-to-noise ratio (SNR) of 20 dB. Furthermore, we evaluate the theoretical latency using the Roofline model, resulting in the air interface latency of 0.491 ms, which satisfies ultra-reliable and low-latency communications (URLLC) latency requirements.

Paper Structure

This paper contains 27 sections, 1 theorem, 17 equations, 7 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model and Problem Statement
  3. System Model
  4. Problem Statement
  5. Channel-Robust and Low-Latency RFF Extraction
  6. Preliminary
  7. Frequency Band Segmentation
  8. Approximation Based on Taylor Expansion
  9. Compensation for the Disparity between Receive Antennas
  10. RFF Extraction Procedure
  11. Impact of Channel and Noise on RFF Estimation Accuracy
  12. Proposed RFF Identification Framework in SIMO Systems
  13. RFF Learning Pipeline
  14. Extraction and Preprocess of RFF
  15. Model Training
  16. ...and 12 more sections

Key Result

Theorem 3.1

The RFF estimate $\hat{T}_0(k)$ is approximately equal to the true value of RFF $T_0(k)$, that is,

Figures (7)

  • Figure 1: System model.
  • Figure 2: System overview.
  • Figure 3: Air interface delay components.
  • Figure 4: Identification accuracy under varying numbers of multipath components, with the frequency band divided across 16 subcarriers.
  • Figure 5: Identification accuracy across different numbers of subcarriers under the 20-path channel.
  • ...and 2 more figures

Theorems & Definitions (2)

  • Theorem 3.1
  • proof