基于朴素贝叶斯的物联网设备指纹算法  

Fingerprint algorithm of IoT devices based on Naive Bayes

作　　者：李琪阳 董雷[1,2] LI Qiyang;DONG Lei(FiberHome Technologies Group,Wuhan 430000,China;Wuhan Science and Technology Co.,Ltd.,Wuhan 430000,China)

机构地区：[1]武汉邮电科学研究院,湖北武汉430000 [2]武汉理工光科股份有限公司,湖北武汉430000

出　　处：《电子设计工程》2021年第21期155-158,共4页Electronic Design Engineering

摘　　要：物联网设备数目庞大且具备一定的网络攻击能力,大多数物联网设备也会涉及用户隐私并关联用户的敏感设备,随着物联网技术的迅捷发展和物联网设备的大规模部署应用,物联网设备带来的安全问题引起了广泛关注。文中针对物联网设备准确识别的问题,引入设备指纹的概念,设计了基于朴素贝叶斯的物联网设备指纹算法,确定了分类器阈值,以此解决设备指纹的更新问题。选取网络摄像头为实验对象,测试了算法的各项性能,实验结果表明,朴素贝叶斯算法的识别准确率可以达到95%以上,漏报率也维持在较低水平,具有可行性。The number of IoT devices is huge and has certain network attack ability.Most of the IoT devices also involve the user's privacy and associate with the sensitive devices of users.With the rapid development of the IoT technology and the large⁃scale deployment and application of IoT devices,the security problems brought by IoT devices have aroused widespread concerns.Aiming at the problem for accurate identification of IoT devices,this paper introduces the concept of device fingerprint,designs the device fingerprint of IoT algorithm based on the Naive Bayes the device fingerprint of IoT,and defines the classifier threshold,to solve the updating problems of the device fingerprint.Taking webcams as examples,the performance of the algorithm was tested.The experimental results show that the recognition accuracy of Naive Bayes algorithm can reach more than 95%,and its false negative rate is also maintained at a low level,proved that the algorithm is feasible.

关 键 词：物联网 设备指纹 朴素贝叶斯 指纹更新 

分 类 号：TN918.91[电子电信—通信与信息系统]