Accurate IoT Device Identification from Merely Packet Length

With the massive deployment of IoT devices, the management of IoT devices becomes more and more important. In this paper, We only need the packet length the device sent to serves in 180s to identify the device. We evaluated the algorithms K-Nearest Neighbor, Random Forest, Suport Vector Machine and Multilayer Perceptron for classification. The results show that the Random Forest is the best and can achieve 99.6% if accuracy in the identification of devices. We also ranked the importance of 10 features related to packet length. Using the five most important features (media, mean, skewness, absolute energy, standard deviation and of packet length), we can achieve 99.5% accuracy on the public dataset and 99.29% accuracy on our dataset.