Device Type Identification via Network Traffic and Lightweight Convolutional Neural Network for Internet of Things

Device type identification (DTI) is one of the most important techniques for the management of Internet of things (IoT). Recently, deep learning (DL) has been considered as a powerful tools for classification or identification, and some researches have introduced DL into DTI for advanced performance. However, DL-based DTI generally has high computational complexity and large model sizes, which are unsuitable for IoT. Thus, we proposed a lightweight convolutional neural network-based DTI with low computational complexity and few model sizes. In detail, we remove the redundant fully-connected layers and replace common convolution with separable convolution. Simulation results demonstrate that lightweight CNN-based DTI just has less than 5% of computational complexity and model size of CNN-based DTI, though there are less than 0.5% performance gap between them.

Abstract licence: CC BY-NC-ND

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.