IoT Device Identification Using Unsupervised Machine Learning

Abstract

Device identification is a fundamental issue in the Internet of Things (IoT). Many critical services, including access control and intrusion prevention, are built on correctly identifying each unique device in a network. However, device identification faces many challenges in the IoT. For example, a common technique to identify a device in a network is using the device’s MAC address. However, MAC addresses can be easily spoofed. On the other hand, IoT devices also include dynamic characteristics such as traffic patterns which could be used for device identification. Machine-learning-assisted approaches are promising for device identification since they can capture dynamic device behaviors and have automation capabilities. Supervised machine-learning-assisted techniques demonstrate high accuracies for device identification. However, they require a large number of labeled datasets, which can be a challenge. On the other hand, unsupervised machine learning can also reach good accuracies without requiring labeled datasets. This paper presents an unsupervised machine-learning approach for IoT device identification.

Comparison and analysis of accuracy of various machine learning algorithms in abnormal state monitoring of internet of things devices

“…This project aims to use machine learning algorithms to analyze sensor data to achieve monitoring and prediction of equipment status [9]. By establishing models of different equipment states and using these models to monitor and predict the current equipment states, production line downtime or other losses caused by equipment failures or anomalies can be effectively avoided [10]. At the same time, through in-depth analysis of historical data, potential problems can be found and corresponding measures can be taken to prevent them.…”