Radio Frequency Fingerprint Identification Based on Deep Complex Residual Network

Shenhua Wang,Jingchao Li,Yulong Ying,Bin Zhang,Xiaofang Fang,Hongliang Jiang

doi:10.1109/access.2020.3037206

Abstract

Radio frequency fingerprint identification is a non-password authentication method based on the physical layer hardware of the communication device. Deep learning methods provide new ideas and techniques for radio frequency fingerprint identification. As a bridge between electromagnetic signal recognition and deep learning, the electromagnetic signal recognition method based on statistical constellation still needs to go through data preprocessing and feature engineering, which is contrary to the end-to-end learning method emphasized by deep learning. Moreover, in the process of converting electromagnetic signal waveform data into images, there is inevitably information loss. Establishing a universal radio frequency fingerprint recognition model suitable for wireless communication scenarios is not only conducive to optimizing the communication system, but also can reduce the cost and time of model selection. Therefore, how to design a deep learning radio frequency fingerprint recognition model suitable for wireless communication is an important problem for researchers. Aiming at the problem that the existing radio frequency fingerprint extraction and identification methods have low recognition rate of communication radiation source individuals, a radio frequency fingerprint identification method based on deep complex residual network is proposed. Through the deep complex residual network, the radio frequency fingerprint feature extraction of the communication radiation source individual is integrated with the recognition process, and an end-to-end deep learning model suitable for wireless communication is established, which greatly improves the identification accuracy of the communication radiation source individuals compared with typical constellation based methods.

Highlights

Common wireless network signals include GSM, CDMA, WCDMA, LTE, WiFi, WiMax, RFID, Bluetooth, ZigBee, Z-Wave, etc
A radio frequency fingerprint identification method based on deep complex residual network is proposed, which is an end-to-end deep learning model suitable for wireless communication
In order to illustrate the effectiveness of the method proposed in this paper, compare it with the radio frequency fingerprint identification method based on contour stellar, and the radio frequency fingerprint identification method based on deep complex convolutional neural network

Summary

Introduction

Common wireless network signals include GSM, CDMA, WCDMA, LTE, WiFi, WiMax, RFID, Bluetooth, ZigBee, Z-Wave, etc. Radio frequency fingerprint identification process extracts the characteristics of the individual information of a specific radiation source from the received signal time series for classification and recognition, which is essentially a pattern recognition problem. When the dimensionality of the radio frequency fingerprint features is too high, dimensionality reduction processing is needed, and the classifier is used for classification and recognition Such methods require an understanding of signal types and features, which can be summarized as feature engineering methods. The radio frequency fingerprint recognition technology based on the waveform domain uses signal samples from the time domain as the basic processing block, which provides the greatest flexibility at the cost of complexity. A radio frequency fingerprint identification method based on deep complex residual network is proposed, which is an end-to-end deep learning model suitable for wireless communication. The deep complex residual network can identify the radio frequency fingerprint of the transmitter, which can greatly improve the identification accuracy of the communication radiation source individuals

Problem description of typical constellation based methods

Application and analysis

Findings

V.Conclusions