摘要
目前关于射频指纹识别(radio frequency fingerprint identification,RFFI)的研究大多基于单个信号特征,存在识别准确率不高的问题。为此,提出了一种多特征融合多任务的射频指纹识别方法。该方法融合功率谱、基于STFT变换的时频谱、互功率谱三种信号特征,采用多任务学习(multi-task learning,MTL)策略,使用噪声信息作为先验知识来帮助网络训练,以设备分类为主任务,以信号噪声含量的分类作为网络第二个任务。仿真实验表明,本文提出的多特征融合多任务的方法较单特征单任务的方法有所提高,是一种有效的射频指纹识别方法。
Most of the current research on Radio Frequency Fingerprint Identification(RFFI)is based on individual’s single signal feature,which has the problem of low identification accuracy.To this end,this paper proposes a multi-feature fusion multi-task RF fingerprint identification method,which fuses three signals:power spectrum,time-frequency spectrum based on STFT trans⁃form,and mutual power spectrum,and uses noise information as a priori knowledge to help network training,with device classifi⁃cation as the main task and classification of signal noise content as the second task of the network for multi-task learning(MTL).Simulation experiments show that the multi-feature fusion multi-task approach proposed in this paper is improved over the singlefeature single-task approach and is an effective method for RF fingerprint identification.
作者
熊松磊
宋甜鑫
苏昱玮
张迪
XIONG Songlei;SONG Tianxin;SU Yuwei;ZHANG Di†(School of Electrical and Information Engineering,Zhengzhou University,Zhengzhou 450001,Henan,China;Henan Key Laboratory of Network Cryptography Technology,Zhengzhou 450001,Henan,China;State Key Laboratory of Space-Ground Integrated Information Technology,Beijing 100086,China)
出处
《武汉大学学报（理学版）》
CAS
CSCD
北大核心
2023年第5期545-552,共8页
Journal of Wuhan University:Natural Science Edition
基金
国家自然科学基金(62001423)
河南省网络密码技术重点实验室项目(LNCT2021-A06)
河南省重点研发与科技推广专项资助(212102210175)
河南省高等学校重点科研项目(21A510011)。
关键词
物理层安全
信号处理
射频指纹
深度学习
特征融合
physical layer security
signal processing
radio frequency fingerprint
deep learning
feature fusion
