Device identification based on communication analysis for the internet of things

Abstract

As the Internet of Things (IoT) is rapidly expanding, a huge variety of devices is being connected to the Internet. Device management is becoming an important topic for IoT. Especially for using devices properly and securely, it is necessary to visualize what types of devices are in the network. However, most conventional device identification methods are not suitable for resource-constrained IoT devices. Therefore, we have developed a method of device identification that identifies the type and model of devices on the basis of general communication information. It determines the type and model of devices by calculating the similarity of features extracted from their network packets. The great merit of our proposed device identifier is that it can be applied to various IoT devices without special equipment. We conducted three experiments to evaluate its effectiveness. In the experiments, we focused on devices specialized for specific functions such as network cameras and factory-used devices because they are effective targets of our device identifier. In addition, we tried identifying models from devices of the same type. The first experiment revealed the relationship between the packet header information used for identification and the success of identification. The second experiment with 11 types of network cameras showed that the device identifier correctly identified nine of them. In addition, the third experiment in a simulated factory environment showed the device identifier correctly identified six types of factory-used devices. Thus, we have demonstrated the feasibility of the proposed device identifier in a real environment.