Encrypted Traffic Categorization based on Flow Byte Sequence Convolution Aggregation Network

Abstract

Traffic categorization aims to classify network traffic into major service types. A modern deep neural network based on temporal sequence modeling is proposed for encrypted traffic categorization. The contemporary techniques such as dilated convolution and residual connection are adopted as the basic building block. The raw traffic files are pre-processed to generate 1-dimensional ow byte sequences and are feed into our specially-devised network. The proposed approach outperforms other existing methods greatly on a public traffic dataset.