Accurate IoT Device Identification based on A Few Network Traffic

The number of devices connected to the Internet has been exploding in recent years, and the wide range of device types poses a serious challenge for asset management and maintenance. We need to know if IoT devices are under cyberattack and if there are devices that violate our privacy, such as pinhole cameras. Traffic-oriented IoT device type identification has become an effective method to prevent cyberattacks and manage assets, but at this stage, in the face of the proliferation of novel IoT devices, the current mainstream IoT device type identification methods are difficult to identify them successfully. At the same time, for a significant number of lightweight IoT devices, most identification methods are simply unable to make correct identifications because the traffic generated by these devices is too little. In this paper, we propose IoT-Siamese, a type identification method for IoT devices based on few-shot traffic, which mainly relies on Siamese network to solve the problem of few samples. Experiments show that our proposed identification method has high identification accuracy for those devices that generate a small volume of traffic, and effectively identify novel devices that join the network.