基于句法模式识别的射频指纹识别方法

陈彦君; 胡爱群

doi:10.11959/j.issn.2096-109x.2025024

您当前的位置：

首页 >

文章列表页 >

基于句法模式识别的射频指纹识别方法

学术论文 | 更新时间：2025-05-14

- 基于句法模式识别的射频指纹识别方法
- Radio frequency fingerprint identification method based on syntactic recognition
- 网络与信息安全学报 2025年11卷第2期页码：152-160
- 作者机构：
  
  1.东南大学信息学院，江苏南京 210096
  2.移动通信全国重点实验室，江苏南京 210096
  3.紫金山实验室，江苏南京 211111
- 作者简介：
  
  [ "陈彦君（2000- ），男，江西九江人，东南大学硕士生，主要研究方向为物理层安全领域的射频指纹技术。" ]
  [ "胡爱群（1963- ），男，江苏如皋人，东南大学教授、博士生导师，主要研究方向为无线物理层安全和移动通信内生安全理论与技术。" ]
- 基金信息：
  
  国家自然科学基金(62171120)
- DOI：10.11959/j.issn.2096-109x.2025024
  中图分类号： TP393
- 收稿：2024-10-25，
  
  修回：2025-03-02，
  
  纸质出版：2025-04-25
- 稿件说明：
移动端阅览
陈彦君, 胡爱群. 基于句法模式识别的射频指纹识别方法[J]. 网络与信息安全学报, 2025, 11(2): 152-160.

CHEN Y J, HU A Q. Radio frequency fingerprint identification method based on syntactic recognition[J]. Chinese Journal of Network and Information Security, 2025, 11(2): 152-160.
陈彦君, 胡爱群. 基于句法模式识别的射频指纹识别方法[J]. 网络与信息安全学报, 2025, 11(2): 152-160. DOI： 10.11959/j.issn.2096-109x.2025024.

CHEN Y J, HU A Q. Radio frequency fingerprint identification method based on syntactic recognition[J]. Chinese Journal of Network and Information Security, 2025, 11(2): 152-160. DOI： 10.11959/j.issn.2096-109x.2025024.

摘要

针对射频指纹特征提取中信道畸变与噪声干扰导致的数据维度高、分类鲁棒性差等问题，提出基于句法模式识别的射频指纹识别方法。以802.11 Wi-Fi信号为对象，通过提取射频指纹幅度谱的拐折特征，构建层次化句法模型以实现特征压缩。首先，将幅度谱的局部形态归纳为峰、谷、上平肩、下平肩4类基元，建立3层句法映射规则：第1层提取单线段特征（平直、上升、下降），第2层组合相邻线段生成双线段特征（如峰、谷），第3层结合特征位置与电平值生成句法序列，进一步提出子图融合算法，通过嵌入、剪枝与拓扑重排，融合同类设备的多样本句法模型，最终将射频指纹特征压缩60%~66%（从50维降至30~33维）。利用10个ESP32-WROOM 32U模组进行实验，在信噪比25 dB下，结合句法模型后，K-近邻（K-nearest neighbor

KNN）和朴素贝叶斯分类器的准确率分别提升4.3%和5.0%，开集识别的类内/类间错误率均低于10.72%。实验结果表明，所提方法在降低数据维度的同时仍能维持高判别性，为射频指纹识别提供了一种新思路。

Abstract

To address the difficulty in feature extraction due to channel characteristics and noise influence

a method based on syntactic pattern recognition was proposed. Using the 802.11 Wi-Fi signal as the object

a hierarchical syntactic model was constructed based on the folding features of the radio frequency fingerprint (RFF) amplitude spectrum to achieve feature compression. The local form of the amplitude spectrum was summarized into four elements: peak

valley

upper flat shoulder

and lower flat shoulder. Three layers of syntactic mapping rules were established. The first layer extracted single line segment features (straight

rise

fall)

the second layer combined adjacent segments to generate double line segment features (e.g.

peak and valley)

and the third layer integrated characteristic position and level value. Additionally

a subgraph fusion algorithm was proposed. Through embedding

pruning

and topology rearrangement

various syntactic models of similar equipment were integrated. Ultimately

the RFF features were compressed by 60% to 66% (from 50 dimensions to 30-33 dimensions). Experiments using 10 ESP32-WROOM 32U modules demonstrate that with a signal-to-noise ratio of 25 dB

the accuracy of the K-nearest neighbor and naive Bayes classifiers is improved by 4.3% and 5.0%

respectively. Both the intra-class error rate and inter-class error rate of open set identification are below 10.72%. This method can reduce data dimensionality while maintaining high discriminability

offering a novel approach for RFF identification.

关键词

Keywords

references

YU J , HU A , ZHOU F , et al . Radio frequency fingerprint identification based on denoising autoencoders [J ] . IEEE Transactions on Information Forensics and Security , 2019 , 14 ( 6 ): 1530 - 1542 .

BASTOS D , SHACKLETON M , EL-MOUSSA F . Internet of things: a survey of technologies and security risks in smart home and city environments [C ] // Living in the Internet of Things: Cybersecurity of the IoT . London, UK : Institution of Engineering and Technology . 2018 .

JIAO L , WANG N , WANG P , et al . Physical layer key generation in 5G wireless networks [J ] . IEEE Wireless Communications , 2019 , 26 ( 5 ): 48 - 54 .

NGUYENN T , ZHENGG , HANZ , et al . Device fingerprinting to enhance wireless security using nonparametric Bayesian method [C ] // 2011 Proceedings IEEE INFOCOM . 2011 : 1404 - 1412 .

PENG L , HU A , ZHANG J , et al . Design of a hybrid RF fingerprint extraction and device classification scheme [J ] . IEEE Internet of Things Journal , 2019 , 6 ( 1 ): 349 - 360 .

PAN Q , AN Z , ZHAO X , et al . The power of precision: high-resolution backscatter frequency drift in RFID identification [J ] . IEEE Transactions on Mobile Computing , 2024 , 23 ( 8 ): 8370 - 8385 .

DANEV B , ZANETTI D , CAPKUN S . On physical-layer identification of wireless devices [J ] . ACM Computing Surveys , 2012 , 45 ( 1 ): Article 6 .

YU J , HU A , LI G , et al . A robust RF fingerprinting approach using multisampling convolutional neural network [J ] . IEEE Internet of Things Journal , 2019 , 6 ( 4 ): 6786 - 6799 .

PENG L , HU A , JIANG Y , et al . A differential constellation trace figure based device identification method for ZigBee nodes [C ] // 2016 8th International Conference on Wireless Communications & Signal Processing (WCSP) . 2016 : 1 - 6 .

俞佳宝 . 射频指纹提取与识别技术研究 [D ] . 南京 : 东南大学 , 2020 .

YU J B . Research on RF fingerprint extraction and identification technology [D ] . Nanjing : Southeast University , 2020 .

GUO Y , HU A , JIANG Y . Deep learning based RF fingerprint identification using cyclic shift characteristic [C ] // 2024 4th International Conference on Consumer Electronics and Computer Engineering (ICCECE) . 2024 : 369 - 374 .

DONG B , HU A , YU J , et al . A robust radio frequency fingerprint extraction method based on channel reciprocity [C ] // 2024 IEEE Wireless Communications and Networking Conference (WCNC) . 2024 : 1 - 6 .

CHOMSKY N . Three models for the description of language [J ] . IEEE Transactions on Information Theory , 1956 , 2 ( 3 ): 113 - 124 .

RAO K , BALCK K . Type classification of fingerprints: a syntactic approach [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 1980 , PAMI-2( 3 ): 223 - 231 .

PISTORI H , CALWAY A , FLACH P . A new strategy for applying grammatical inference to image classification problems [C ] // 2013 IEEE International Conference on Industrial Technology (ICIT) . 2013 : 1032 - 1037 .

LI X , SONG X , WU T . AOGNets: compositional grammatical architectures for deep learning [EB ] .

ZARCHI M S , TAN R T , VAN-GEMEREN C , et al . Understanding image concepts using ISTOP model [J ] . Pattern Recognition , 2016 , 53 : 174 - 183 .

ASTOLFI G , REZENDE F , PORTO J , et al . Syntactic pattern recognition in computer vision: A systematic review [J ] . ACM Computing Surveys , 2021 , 54 ( 3 ): Article 65 .

VISNEVSKI N , KRISHNAMURTHY V , WANG A , et al . Syntactic modeling and signal processing of multifunction radars: a stochastic context-free grammar approach [J ] . Proceedings of the IEEE , 2007 , 95 ( 5 ): 1000 - 1025 .

OU J , CHENY , ZHAOF , et al . Novel method for radar word extraction in the syntactic model of multi-function radar [C ] // 2017 18th International Radar Symposium (IRS) . 2017 : 1 - 7 .

李莹 , 陈艺廷 , 李鸿 . 基于句法模式识别的雷达识别方法研究 [J ] . 现代电子技术 , 2014 .

LI Y , CHEN Y T , LI H . Research on radar recognition method based on syntactic pattern recognition [J ] . Modern Electronic Technology , 2014 , 37 : 25 - 28 .

陈天舒 . Wi-Fi射频指纹提取与识别技术研究 [D ] . 南京 : 东南大学 , 2021 .

CHEN T S . Wi-Fi radio frequency fingerprint extraction and identification technology [D ] . Nanjing : Southeast University , 2021 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据