基于LR-ODCNN的物联网设备射频指纹信号识别方法  

Radio frequency fingerprint signal recognition method for internet of things devices based on LR-ODCNN

作　　者：农鑫 卿国能 朱康奇 张振荣[1] 郑嘉利[1] NONG Xin;QING Guoneng;ZHU Kangqi;ZHANG Zhenrong;ZHENG Jiali(School of Computer,Electronic and Information,Guangxi University,Nanning 530004,China;Depatment of Electronic Engineering,Tsinghua University,Beijing 100084,China)

机构地区：[1]广西大学计算机与电子信息学院,南宁530004 [2]清华大学电子工程系,北京100084

出　　处：《光通信技术》2024年第3期68-73,共6页Optical Communication Technology

基　　金：广西重点研发计划项目(桂科AB22080048)资助。

摘　　要：为了解决物联网环境下设备众多且终端资源有限带来的安全问题,提出了一种基于轻量级全维动态卷积神经网络(LR-ODCNN)的物联网设备射频指纹信号识别方法。首先,设计了LR-ODCNN模型;然后,利用光传输系统采集设备的基带信号,从基带信号中提取I、Q信号作为网络的输入;最后,LR-ODCNN模型根据多维注意力机制来适应不同设备的信号特征,并进行信号特征的提取和识别。实验结果表明,当传输距离为10 m、400 m、1.7 km和8.6 km时,LR-ODCNN模型的平均识别准确率为94.35%,比Mc AFF模型、Oracle模型分别提高了5.35%、10.13%,且具有鲁棒性强、轻量化的优点。In order to address the security problem arising from the numerous devices and limited terminal resources in the inter-net of things(IoT)environment,a method for radio frequency(RF)fingerprint signal recognition of IoT devices based on lightweight omni-dimensional dynamic convolutional neural network(LR-ODCNN)is proposed.Firstly,the LR-ODCNN model is designed.Then,the baseband signals of the devices are collected using an optical transmission system,and the I and Q signals are extracted from the baseband signals as the input to the network.Finally,the LR-ODCNN model adapts to the signal character-istics of different devices based on a multi-dimensional attention mechanism and performs signal feature extraction and recogni-tion.The experimental results show that the average recognition accuracy of the LR-ODCNN model is 94.35%at transmission dis-tances of 10 m,400 m,1.7 km,and 8.6 km.,which is an improvement of 5.35%and 10.13%compared to the McAFF model and the Oracle model respectively.Additionally,it boasts strong robustness and lightweight.

关 键 词：物联网安全 设备识别 全维动态卷积 射频指纹识别 深度学习 

分 类 号：TN975[电子电信—信号与信息处理]