基于信息增益的无线通信信号指纹构建及识别机制研究

黄伟庆; 杨召阳; 魏冬; 张萌; 王文; 叶彬

引用本文：

黄伟庆,杨召阳,魏冬,张萌,王文,叶彬.基于信息增益的无线通信信号指纹构建及识别机制研究[J].信息安全学报,2020,5(6):11-26 [点击复制]
HUANG Weiqing,YANG Zhaoyang,WEI Dong,ZHANG Meng,WANG Wen,YE Bin.Fingerprint construction and identity recognition of Wireless signal based on information gain[J].Journal of Cyber Security,2020,5(6):11-26 [点击复制]

本文已被：浏览 5246次下载 4746次	码上扫一扫！
基于信息增益的无线通信信号指纹构建及识别机制研究
黄伟庆^1,2, 杨召阳^1,2, 魏冬^1,2, 张萌^1,2, 王文^1,2, 叶彬^1,2
0 字体:加大+\|默认\|缩小-
(1.中国科学院信息工程研究所北京中国 100093;2.中国科学院大学北京中国 100049)

摘要:

为实现对特定区域电磁空间的有效监管，本文建立针对无线通信信号的唯一识别及标定机制，利用无线通信信号调制方式、发射机器件一致性及通信协议等多种因素造成的信号差异，构建表征无线通信信号完备差异信息的指纹集，并引入信息增益评价机制评估指纹集中各特征对差异信息的贡献度，建立精简有效的电磁指纹。在此基础上，设计基于支持向量机的指纹匹配算法，实现无线通信信号身份的有效识别。仿真实验结果表明，本文方法在接收信噪比大于4 dB时可实现特定区域电磁空间内无线通信信号身份的有效识别。

关键词: 无线通信信号指纹信息增益身份识别

DOI：10.19363/J.cnki.cn10-1380/tn.2020.11.02

投稿时间：2018-12-27修订日期：2019-03-13

基金项目:本课题得到国家自然科学基金项目（No.61501458）资助，中国科学院战略性先导C类XDC02000000专项支持。

Fingerprint construction and identity recognition of Wireless signal based on information gain

HUANG Weiqing^1,2, YANG Zhaoyang^1,2, WEI Dong^1,2, ZHANG Meng^1,2, WANG Wen^1,2, YE Bin^1,2

(1.Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China;2.University of Chinese Academy of Sciences, Beijing 100049, China)

Abstract:

With the question of supervising of the special electromagnetic space. This paper aims to construct the unique identity of the wireless signal. Through fusing the wireless signal difference features caused by modulation type, device uniformity and communication protocol, the fingerprint set of wireless signal is constructed. Meanwhile, aiming at evaluating the fingerprint contribution degree to identity recognition of signal and constructing refined and valid fingerprint set, this paper introduces into the information gain to evaluate every fingerprint’s degree to identity recognition and support vector machine (SVM) method to match refined fingerprint subset. Simulation and experiment results show that, this paper’s fingerprint set method can effectively distinguish the identity of different wireless signal in special electromagnetic space under the condition that the signal-noise ratio is larger than 4 dB.

Key words: wireless signal fingerprint information gain identity recognition