体域网中基于CSI指纹的身份认证算法研究  

Identity Authentication Algorithm Based on CSI Fingerprint In Body Area Network

作　　者：丁佳蓉 钟伯成[1] 朱淑文 DING Jia-rong;ZHONG Bo-cheng;ZHU Shu-wen(School of Electronic and Electrical Engineering,Shanghai University of Engineering Science,Shanghai 201620,China)

机构地区：[1]上海工程技术大学电子电气工程学院,上海201620

出　　处：《测控技术》2020年第5期96-100,共5页Measurement & Control Technology

基　　金：国家自然科学基金项目(61603242,61702322)。

摘　　要：无线体域网是实现智慧健康的重要基础,但其采集的生理状态等敏感信息在开放的无线信道传输,攻击者容易伪装成合法用户获取用户隐私数据,因而身份认证成为挑战。对此,提出了一种将无线信道特征CSI与递归神经网络(RNN)相结合的身份认证方法,实现体域网中节点的有效身份认证。利用无线体域网中无线信道的物理层特征CSI作为合法节点认证的指纹特征。为了加快认证速度与效率,通过取特定环境下CSI的数据包,将数据包中子载波的特性作为RNN的输入量,训练出RNN模型来快速识别合法节点。通过实验将所提出的身份认证方法与利用RSS作为指纹特征的认证方法进行比较,结果表明所提方法的认证速度更快、准确率更高。The wireless body area network( WBAN) is an important foundation for realizing intelligent health.However,sensitive information such as the collected physiological state is transmitted over an open wireless channel,and attackers can easily disguise as legitimate users to obtain user privacy data,and identity authentication becomes a challenge. In this regard,an identity authentication method combining wireless channel feature CSI with recurrent neural network( RNN) is proposed to achieve effective identity authentication of nodes in the body area network. The physical layer feature CSI of the wireless channel in the WBAN was used as the fingerprint feature of the legal nodes authentication. In order to speed up the authentication speed and efficiency,the RNN model was trained to quickly identify the legal nodes by taking the CSI data packet in the specific environment and using the characteristics of the subcarriers in the data packet as the input of the RNN. The proposed identity authentication method is compared with the authentication method using RSS as the fingerprint feature through experiments. The results show that the proposed method has faster authentication speed and higher accuracy.

关 键 词：体域网 指纹特征 神经网络 模仿攻击 可穿戴传感器 

分 类 号：TP212.3[自动化与计算机技术—检测技术与自动化装置]