Improving the network traffic classification using the Packet Vision approach

TL;DR

This paper introduces Packet Vision, a novel method that converts raw network packet data into images for CNN-based traffic classification, enhancing security and privacy while achieving high accuracy.

Contribution

The paper presents a new image-based packet representation method and evaluates its effectiveness with multiple CNN architectures for traffic classification.

Findings

Packet Vision outperforms existing methods in accuracy.

CNN architectures like AlexNet, ResNet-18, and SqueezeNet are effective.

The approach enhances security and privacy in traffic analysis.

Abstract

The network traffic classification allows improving the management, and the network services offer taking into account the kind of application. The future network architectures, mainly mobile networks, foresee intelligent mechanisms in their architectural frameworks to deliver application-aware network requirements. The potential of convolutional neural networks capabilities, widely exploited in several contexts, can be used in network traffic classification. Thus, it is necessary to develop methods based on the content of packets transforming it into a suitable input for CNN technologies. Hence, we implemented and evaluated the Packet Vision, a method capable of building images from packets raw-data, considering both header and payload. Our approach excels those found in state-of-the-art by delivering security and privacy by transforming the raw-data packet into images. Therefore, we built a dataset with four traffic classes evaluating the performance of three CNNs architectures: AlexNet, ResNet-18, and SqueezeNet. Experiments showcase the Packet Vision combined with CNNs applicability and suitability as a promising approach to deliver outstanding performance in classifying network traffic.