Encrypted traffic classification method based on parallel traffic graph and graph neural network

Aiming at the problems of traditional encrypted traffic classification methods limited by the imbalance of dataset classes and the unreliability of the features used in complex network environments, an encrypted traffic classification method based on parallel traffic graph and graph neural network w...

Full description

Saved in:
Bibliographic Details
Main Authors: LIU Taotao, FU Yu, YU Yihan, AN Yishuai
Format: Article
Language:zho
Published: Editorial Department of Journal on Communications 2025-06-01
Series:Tongxin xuebao
Subjects:
Online Access:http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2025095/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849709243252342784
author LIU Taotao
FU Yu
YU Yihan
AN Yishuai
author_facet LIU Taotao
FU Yu
YU Yihan
AN Yishuai
author_sort LIU Taotao
collection DOAJ
description Aiming at the problems of traditional encrypted traffic classification methods limited by the imbalance of dataset classes and the unreliability of the features used in complex network environments, an encrypted traffic classification method based on parallel traffic graph and graph neural network was proposed. Firstly, the traffic graphs were constructed from the packet header and payload perspectives to emphasize their differences. Then, an improved graph attention network was introduced to extract effective information from the parallel traffic graphs. Next, a feature cross-fusion attention module was used to fuse the extracted information, achieving a more robust feature representation. Finally, classification was performed using fully connected layers and a Softmax layer. Experiments show that the proposed method achieves better results on the ISCX-VPN, ISCX-nonVPN, ISCX-Tor, and ISCX-nonTor datasets, with accuracies of 96.88%, 90.62%, 99.24%, and 98.13%, respectively, significantly enhancing encrypted traffic classification performance.
format Article
id doaj-art-5cbb76a39d5145ddbc56b111c23d25ee
institution DOAJ
issn 1000-436X
language zho
publishDate 2025-06-01
publisher Editorial Department of Journal on Communications
record_format Article
series Tongxin xuebao
spelling doaj-art-5cbb76a39d5145ddbc56b111c23d25ee2025-08-20T03:15:22ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2025-06-01464559114257081Encrypted traffic classification method based on parallel traffic graph and graph neural networkLIU TaotaoFU YuYU YihanAN YishuaiAiming at the problems of traditional encrypted traffic classification methods limited by the imbalance of dataset classes and the unreliability of the features used in complex network environments, an encrypted traffic classification method based on parallel traffic graph and graph neural network was proposed. Firstly, the traffic graphs were constructed from the packet header and payload perspectives to emphasize their differences. Then, an improved graph attention network was introduced to extract effective information from the parallel traffic graphs. Next, a feature cross-fusion attention module was used to fuse the extracted information, achieving a more robust feature representation. Finally, classification was performed using fully connected layers and a Softmax layer. Experiments show that the proposed method achieves better results on the ISCX-VPN, ISCX-nonVPN, ISCX-Tor, and ISCX-nonTor datasets, with accuracies of 96.88%, 90.62%, 99.24%, and 98.13%, respectively, significantly enhancing encrypted traffic classification performance.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2025095/encrypted traffic classificationdeep learninggraph neural networkfeature fusion
spellingShingle LIU Taotao
FU Yu
YU Yihan
AN Yishuai
Encrypted traffic classification method based on parallel traffic graph and graph neural network
Tongxin xuebao
encrypted traffic classification
deep learning
graph neural network
feature fusion
title Encrypted traffic classification method based on parallel traffic graph and graph neural network
title_full Encrypted traffic classification method based on parallel traffic graph and graph neural network
title_fullStr Encrypted traffic classification method based on parallel traffic graph and graph neural network
title_full_unstemmed Encrypted traffic classification method based on parallel traffic graph and graph neural network
title_short Encrypted traffic classification method based on parallel traffic graph and graph neural network
title_sort encrypted traffic classification method based on parallel traffic graph and graph neural network
topic encrypted traffic classification
deep learning
graph neural network
feature fusion
url http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2025095/
work_keys_str_mv AT liutaotao encryptedtrafficclassificationmethodbasedonparalleltrafficgraphandgraphneuralnetwork
AT fuyu encryptedtrafficclassificationmethodbasedonparalleltrafficgraphandgraphneuralnetwork
AT yuyihan encryptedtrafficclassificationmethodbasedonparalleltrafficgraphandgraphneuralnetwork
AT anyishuai encryptedtrafficclassificationmethodbasedonparalleltrafficgraphandgraphneuralnetwork