Fingerprint Recognition and Classification of IoT Devices Based on Z-Wave

With the popularity of Internet of Things (IoT) devices, such as smart sockets and smart sensors, etc. The security of the Internet of Things network system will be a crucial issue. Cyber attackers can bypass traditional security solutions by spoofing the gateway to pretend to be a legitimate device in the system, waiting for an opportunity to access the system, and IoT device fingerprint recognition is extra important. However, most of the existing recognition schemes are based on traditional machine learning classification algorithms, the recognition rate of the scheme is not high, and traditional recognition algorithms will have problems such as overlapping recognition. This article proposes a device fingerprint identification scheme based on deep learning for IoT devices with Z-Wave protocol, and proposes the concept of confidence interval to solve the problem of overlapping identification of similar devices. Experimental results show that the average recognition accuracy of the scheme reaches 90.2%.