TCGNN: Packet-grained network traffic classification via Graph Neural Networks

Abstract

Network traffic classification is the fundamental and vital function for network management, network security and so on. With the traffic scenarios becoming more and more complex, current commonly used practices, e.g., port-based and payload-based classification methods, can hardly work. Even though the new emerging resorts, i.e., machine learning or deep learning methods, have increased classification accuracy, the performance is still under improvement. To improve the classification accuracy and performance, we propose a novel Graph Neural Network (GNN) based Traffic Classification proposal named TCGNN considering the insight of observing packets from a graph aspect. TCGNN first transforms each network packet into an undirected graph. Then it adopts a two-layer graph convolutional network with three different aggregation strategies so as to learn the latent application representation from the packet-transformed graph. Finally, relying on GNN’s powerful ability in learning graph representation, TCGNN can identify unknown network packets with an extremely high accuracy rate. Extensive experiments on two real-world traffic classification datasets demonstrate the superior effectiveness of TCGNN over the existing packet-grained traffic classification methods.