Radio Frequency Fingerprinting Identification of Few-Shot Wireless Signals Based on Deep Metric Learning

As a cross-protocol endogenous security mechanism, the physical layer-based radio frequency (RF) fingerprinting can effectively enhance the existing password-based application layer authentication utilizing the hardware differences of wireless devices, which is unique and cannot be counterfeited by...

Full description

Saved in:
Bibliographic Details
Published in:Wireless communications and mobile computing 2023-09, Vol.2023, p.1-13
Main Authors: Zhao, Caidan, Yu, Jinhui, Luo, Gege, Wu, Zhiqiang
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Big Data
Biometric recognition systems
Cell phones
Cellular telephones
Classification
Deep learning
Fingerprint verification
Hypotheses
Identification
Internet of Things
Machine learning
Neural networks
Radio frequency
Signal classification
Target recognition
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:As a cross-protocol endogenous security mechanism, the physical layer-based radio frequency (RF) fingerprinting can effectively enhance the existing password-based application layer authentication utilizing the hardware differences of wireless devices, which is unique and cannot be counterfeited by a third party. However, the recognition performance of the deep learning physical layer fingerprint recognition algorithm drops sharply in the case of a small number of signal samples. This paper analyzes the feasibility and proposes the few-shot wireless signal classification network based on deep metric learning (FSig-Net). FSig-Net reduces the model’s dependence on big data by adaptively learning the feature distance metric. We use 8 mobile phones and 18 Internet of Things (IoT) modules as targets for identification. When the number of single-type samples is only 10, the recognition accuracy of mobile phones can reach 98.28%, and the recognition accuracy of IoT devices can reach 98.20%.
ISSN:1530-8669
1530-8677
DOI:10.1155/2023/2132148