一种新的基于信号导频的射频指纹识别方法

曾盛; 朱丰超; 杨剑

doi:10.13700/j.bh.1001-5965.2021.0164

一种新的基于信号导频的射频指纹识别方法

doi: 10.13700/j.bh.1001-5965.2021.0164

曾盛¹,
朱丰超^1, ,,
杨剑²

1.
火箭军工程大学作战保障学院，西安 710025
2.
火箭军工程大学导弹工程学院，西安 710025

基金项目:

国家自然科学基金 61601474

国家自然科学基金 62071480

详细信息

通讯作者:
朱丰超, E-mail: fengchao_zhu@126.com

中图分类号: TN918.91
计量
- 文章访问数: 482
- HTML全文浏览量: 101
- PDF下载量: 45
- 被引次数: 0
出版历程
- 收稿日期: 2021-04-01
- 录用日期: 2021-06-20
- 网络出版日期: 2021-07-12
- 整期出版日期: 2022-12-20

A new RF fingerprint identification method based on preamble of signal

1.
Combat Support Academy, Rocket Force University of Engineering, Xi'an 710025, China
2.
Missile Engineering Academy, Rocket Force University of Engineering, Xi'an 710025, China

Funds:

National Natural Science Foundation of China 61601474

National Natural Science Foundation of China 62071480

More Information

Corresponding author: ZHU Fengchao, E-mail: fengchao_zhu@126.com

摘要

摘要:
现有基于深度学习的射频指纹识别技术大多采用原始数据样本作为网络输入，未考虑信号携带内容对分类结果产生的影响，网络结构相对单一。为此，针将信号导频部分作为网络输入展开了研究，提出了一种新的导频提取算法，对10个ADALM-PLUTO软件定义无线电设备(SDR)辐射出的信号提取其导频，并建立了3种不同距离条件下的导频数据集。提出将Inception网络结构用于射频指纹识别，在10 m无线传输距离下达到了98.58%的分类精度，相较于现有基于AlexNet网络改进的卷积神经网络(CNN)，分类精度有所提升。
- 射频指纹识别 /
- 深度学习 /
- 无线通信 /
- 导频提取 /
- 卷积神经网络
Abstract:
Deep learning-based RF fingerprint recognition methods now primarily use raw data samples as the input of the network, never taking into account how the signal's content affects classification outcomes, and the structure of the network is relatively simple. In response to the above problems, the preamble of the signal as the input of the network was studied and we proposed a new preamble extraction algorithm.We extracted the preamble of 10 ADALM-PLUTO software-defined radios (SDR) and built the preamble data sets at three different distances.The Inception network structure is proposed to be used in RF fingerprint identification in this paper, and the classification accuracy is still 98.58% under the wireless transmission distance of 10 m. The classification accuracy is increased as compared to the pre-existing convolutional neural network (CNN) built on the AlexNet network.
- radio frequency fingerprint identification /
- deep learning /
- wireless communication /
- preamble extraction /
- convolutional neural network

HTML全文

图 1 通信系统模型

Figure 1. Communication system model

下载: 全尺寸图片幻灯片

图 2 物理层帧结构

Figure 2. Frame structure of physical layer

下载: 全尺寸图片幻灯片

图 3 发送端信号处理过程

Figure 3. Signal processing at transmitter

下载: 全尺寸图片幻灯片

图 4 无线通信流程框架

Figure 4. Frame diagram of wireless communication

下载: 全尺寸图片幻灯片

图 5 精频率补偿算法框图

Figure 5. Block diagram of fine frequency compensation algorithm

下载: 全尺寸图片幻灯片

图 6 滑动过程

Figure 6. Sliding process

下载: 全尺寸图片幻灯片

图 7 算法框架

Figure 7. Framework of algorithm

下载: 全尺寸图片幻灯片

图 8 导频检测结果

Figure 8. Preamble extraction results

下载: 全尺寸图片幻灯片

图 9 本文使用的Inception网络结构

Figure 9. Inception network used in this paper

下载: 全尺寸图片幻灯片

图 10 Inception模块结构

Figure 10. Structure of Inception module

下载: 全尺寸图片幻灯片

图 11 ADALM-PLUTO软件定义无线电设备和工作站

Figure 11. ADALM-PLUTO software-defined radio equipment and workstation

下载: 全尺寸图片幻灯片

图 12 三种网络的分类结果

Figure 12. Classification results of three kinds of networks

下载: 全尺寸图片幻灯片

图 13 1 m和10 m距离下3种网络分类结果对比

Figure 13. Comparisons of classification results of three networks at 1 m and 10 m

下载: 全尺寸图片幻灯片

表 1 2.45 GHz Symbol-to-Chip映射关系

Table 1. Mapping relationship of 2.45 GHz Symbol-to-Chip

s_i	chip_i^1×32
s₀：0000	chip₀^1×32：1 1 0 1 1 0 0 1 1 1 0 0 0 0 1 1 0 1 0 1 0 0 1 0 0 0 1 0 1 1 1 0
s₁：0001	chip₁^1×32：1 1 1 0 1 1 0 1 1 0 0 1 1 1 0 0 0 0 1 1 0 1 0 1 0 0 1 0 0 0 1 0
s₂：0010	chip₂^1×32：0 0 1 0 1 1 1 0 1 1 0 1 1 0 0 1 1 1 0 0 0 0 1 1 0 1 0 1 0 0 1 0
s₃：0011	chip₃^1×32：0 0 1 0 0 0 1 0 1 1 1 0 1 1 0 1 1 0 0 1 1 1 0 0 0 0 1 1 0 1 0 1
s₄：0100	chip₄^1×32：0 1 0 1 0 0 1 0 0 0 1 0 1 1 1 0 1 1 0 1 1 0 0 1 1 1 0 0 0 0 1 1
s₅：0101	chip₅^1×32：0 0 1 1 0 1 0 1 0 0 1 0 0 0 1 0 1 1 1 0 1 1 0 1 1 0 0 1 1 1 0 0
s₆：0110	chip₆^1×32：1 1 0 0 0 0 1 1 0 1 0 1 0 0 1 0 0 0 1 0 1 1 1 0 1 1 0 1 1 0 0 1
s₇：0111	chip₇^1×32：1 0 0 1 1 1 0 0 0 0 1 1 0 1 0 1 0 0 1 0 0 0 1 0 1 1 1 0 1 1 0 1
s₈：1000	chip₈^1×32：1 0 0 0 1 1 0 0 1 0 0 1 0 1 1 0 0 0 0 0 0 1 1 1 0 1 1 1 1 0 1 1
s₉：1001	chip₉^1×32：1 0 1 1 1 0 0 0 1 1 0 0 1 0 0 1 0 1 1 0 0 0 0 0 0 1 1 1 0 1 1 1
s₁₀：1010	chip₁₀^1×32：0 1 1 1 1 0 1 1 1 0 0 0 1 1 0 0 1 0 0 1 0 1 1 0 0 0 0 0 0 1 1 1
s₁₁：1011	chip₁₁^1×32：0 1 1 1 0 1 1 1 1 0 1 1 1 0 0 0 1 1 0 0 1 0 0 1 0 1 1 0 0 0 0 0
s₁₂：1100	chip₁₂^1×32：0 0 0 0 0 1 1 1 0 1 1 1 1 0 1 1 1 0 0 0 1 1 0 0 1 0 0 1 0 1 1 0
s₁₃：1101	chip₁₃^1×32：0 1 1 0 0 0 0 0 0 1 1 1 0 1 1 1 1 0 1 1 1 0 0 0 1 1 0 0 1 0 0 1
s₁₄：1110	chip₁₄^1×32：1 0 0 1 0 1 1 0 0 0 0 0 0 1 1 1 0 1 1 1 1 0 1 1 1 0 0 0 1 1 0 0
s₁₅：1111	chip₁₅^1×32：1 1 0 0 1 0 0 1 0 1 1 0 0 0 0 0 0 1 1 1 0 1 1 1 1 0 1 1 1 0 0 0

下载: 导出CSV

表 2 网络复杂度对比

Table 2. Network complexity comparison

网络	Flops/次	网络参数量	网络训练时间/s
Inception	183 066 880	137 610	4 166
文献[11-12]	348 888 640	146 700	1 218
文献[14]	126 8891 200	188 590	2 421

下载: 导出CSV

参考文献(17)

[1]	任品毅, 徐东阳. 无线物理层认证技术: 昨天、今天和明天[J]. 中兴通讯技术, 2020, 26(4): 58-66. https://www.cnki.com.cn/Article/CJFDTOTAL-ZXTX202004016.htm REN P Y, XU D Y. Wireless physical layer authentication technology: Yesterday, today, and tomorrow[J]. ZTE Communications, 2020, 26(4): 58-66(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-ZXTX202004016.htm
[2]	俞佳宝, 胡爱群, 朱长明, 等. 无线通信设备的射频指纹提取与识别方法[J]. 密码学报, 2016, 3(5): 433-446. https://www.cnki.com.cn/Article/CJFDTOTAL-MMXB201605002.htm YU J B, HU A Q, ZHU C M, et al. RF fingerprinting extraction and identification of wireless communication devices[J]. Journal of Cryptologic Research, 2016, 3(5): 433-446(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-MMXB201605002.htm
[3]	张振, 贾济铖, 康健, 等. 射频指纹识别技术方法综述[J]. 无线电通信技术, 2021, 47(3): 249-258. https://www.cnki.com.cn/Article/CJFDTOTAL-WXDT202103001.htm ZHANG Z, JIA J C, KANG J, et al. Overview of RF fingerprint identification technology methods[J]. Radio Communications Technology, 2021, 47(3): 249-258(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-WXDT202103001.htm
[4]	曾勇虎, 陈翔, 林云, 等. 射频指纹识别的研究现状及趋势[J]. 电波科学学报, 2020, 35(3): 305-315. https://www.cnki.com.cn/Article/CJFDTOTAL-DBKX202003001.htm ZENG Y H, CHEN X, LIN Y, et al. Review of radio frequency fingerprinting identification[J]. Chinese Journal of Radio Science, 2020, 35(3): 305-315(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-DBKX202003001.htm
[5]	CHOE H C, POOLE C E, YU A M, et al. Novel identification of intercepted signals from unknown radio transmitters[C] // Proceedings of SPIE-The International Society for Optical Engineering, 1995, 2491: 504-517.
[6]	郑娜娥, 王盛, 张靖志, 等. 基于射频指纹的辐射源个体识别技术综述[J]. 信息工程大学学报, 2020, 21(3): 285-289. https://www.cnki.com.cn/Article/CJFDTOTAL-XXGC202003006.htm ZHENG N E, WANG S, ZHANG J Z, et al. Overview of emitter identification techniques based on radio frequency fingerprinting[J]. Journal of Information Engineering University, 2020, 21(3): 285-289(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-XXGC202003006.htm
[7]	URETEN O, SERINKEN N. Detection of radio transmitter turn-on transients[J]. Electronics Letters, 1999, 35(23): 1996-1997.
[8]	KENNEDY I O, SCANLON P, MULLANY F J, et al. Radio transmitter fingerprinting: A steady state frequency domain approach[C] // 2008 IEEE 68th Vehicular Technology Conference. Piscataway: IEEE Press, 2008: 1-5.
[9]	SUSKI W C, TEMPLE M A, MENDENHALL M J, et al. Using spectral fingerprints to improve wireless network security[C] //IEEE GLOBECOM 2008-2008 IEEE Global Telecommunications Conference. Piscataway: IEEE Press, 2008: 1-5.
[10]	王培. 基于稳态信号的射频指纹算法的研究[D]. 成都: 电子科技大学, 2020: 20-52. WANG P. Research on RF fingerprint algorithm based on steady state signal[D]. Chengdu: University of Electronic Science and Technology of China, 2020: 20-52(in Chinese).
[11]	RIYAZ S, SANKHE K, IOANNIDIS S, et al. Deep learning convolutional neural networks for radio identification[J]. IEEE Communications Magazine, 2018, 56(9): 146-152.
[12]	SANKHE K, BELGIOVINE M, FAN Z, et al. ORACLE: Optimized radio classification through convolutional neural networks[EB/OL]. (2018-12-03)[2020-12-13]. https://arxiv.org/abs/1812.01124v1.
[13]	秦嘉. 基于深度学习的通信辐射源个体识别[D]. 北京: 北京邮电大学, 2019: 22-23. QIN J. Individual identification of communication emmiter based on deep learning[D]. Beijing: Beijing University of Posts and Telecommunications, 2019: 22-23(in Chinese).
[14]	ELMAGHBUB A, HAMDAOUI B. Leveraging hardware-impaired out-of-band information through deep neural networks for robust wireless device classification[EB/OL]. (2020-04-23)[2021-03-28]. https://arxiv.org/abs/2004.11126v1.
[15]	IEEE 802.15 Working Group. IEEE stardard for low-rate wireless networks: IEEE 802.15.4[S]. Piscataway: IEEE, 2006.
[16]	SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[EB/OL]. (2014-09-17)[2021-03-28]. https://arxiv.org/abs/1409.4842.
[17]	RICE M. Digital communications: A discrete-time approach[M]. New York: Pearson Education India, 2009.