LI Xinjie,WU Zhen.Network Traffic Classification based on Attention Mechanism and Convolutional Neural Network[J].Journal of Chengdu University of Information Technology,2026,41(01):39-46.[doi:10.16836/j.cnki.jcuit.2026.01.006]
基于注意力机制和卷积神经网络的网络流量分类
- Title:
- Network Traffic Classification based on Attention Mechanism and Convolutional Neural Network
- 文章编号:
- 2096-1618(2026)01-0039-08
- Keywords:
- raw network traffic; classification; attention mechanism; convolution
- 分类号:
- TP391
- 文献标志码:
- A
- 摘要:
- 网络流量分类作为保障网络服务质量、网络安全检测的关键技术,对有效管理和保护网络环境具有重要意义。然而,在当前复杂的网络环境中,传统的流量识别分类方法,如端口检测、深度包检测,已经难以应对挑战,且单一的神经网络结构特征提取不充分。鉴于此,提出一种新的双通道恶意流量识别分类算法模型,该模型无需特征工程,结合多头注意力机制、逐点卷积和深度卷积的思想,对原始网络流量进行序列、空间的特征提取以及学习。在USTC-TFC2016公开数据集上进行实验,结果表明,提出的分类模型在二分类、常规流量十分类、恶意流量十分类、二十分类中都有很高的准确率,分别达到了100%、99.9%、98.6%、99%。
- Abstract:
- As a key technology to ensure network service quality and network security detection, network traffic classification is of great significance for the effective management and protection of network environment. However, in the current complex network environment, the traditional traffic identification and classification methods, such as port detection and deep packet inspection, have been unable to cope with the challenge, and the single neural network structure feature extraction is insufficient. In view of this, a new dual-channel malicious traffic identification and classification algorithm model is proposed. This model does not require any feature engineering. It combines the ideas of multi-head attention mechanism, pointwise convolution and depthwise convolution to extract and learn the features of the raw network traffic in sequence and space. Experiments are conducted on the USTC-TFC2016 public dataset. The results show that the proposed classification model has high accuracy in binary classification, benign traffic ten categories, malicious traffic ten categories, and twenty categories, reaching 100%, 99.9%, 98.6%, and 99% respectively.
参考文献/References:
[1] 中国互联网络信息中心发布第52次《中国互联网络发展状况统计报告》[J].国家图书馆学刊,2023,32(5):13.
[2] Azab A,Khasawneh M,Alrabaee S,et al.Network traffic classification:Techniques,datasets,and challenges[J].Digital Communications and Networks,2024,10(3):676-692.
[3] Khandait P,Hubballi N,Mazumdar B.Efficient keyword matching for deep packet inspection based network traffic classification[C].proceedings of the 2020 International Conference on COMmunication Systems & NETworkS(COMSNETS).2020:567-570.
[4] Moore A W,Zuev D.Internet traffic classification using bayesian analysis techniques [C].Proceedings of the 2005 ACM SIGMETRICS international conference on Measurement and modeling of computer systems.Banff,Alberta,Canada; Association for Computing Machinery.2005:50-60.
[5] Wang Z.The Applications of Deep Learning on Traffic Identification[C/OL].Black Hat USA Briefings,2015.
[6] Wang W,Zhu M,Wang J,et al.End-to-end encrypted traffic classification with one-dimensional convolution neural networks[C].proceedings of the 2017 IEEE International Conference on Intelligence and Security Informatics(ISI).2017:43-48.
[7] Lotfollahi M,Jafari Siavoshani M,Shirali Hossein Zade R,et al.Deep packet: A novel approach for encrypted traffic classification using deep learning[J].Soft Computing,2020,24(3):1999-2012.
[8] Li R,Xiao X,Ni S,et al.Byte Segment Neural Network for Network Traffic Classification[C].proceedings of the 2018 IEEE/ACM 26th International Symposium on Quality of Service(IWQoS),2018:1-10.
[9] Bu Z,Zhou B,Cheng P,et al.Encrypted Network Traffic Classification Using Deep and Parallel Network-in-Network Models [J].IEEE Access,2020,8:132950-132959.
[10] Lin X,Xiong G,Gou G,et al.ET-BERT:A Contextualized Datagram Representation with Pre-training Transformers for Encrypted Traffic Classification [C].Proceedings of the ACM Web Conference 2022,2022:633-642.
[11] Vaswani A,Shazeer N,Parmar N,et al.Attention is all you need[C].Advances in Neural Information Processing Systems 30,2017:6000-6010.
[12] Han K,Wang Y,Tian Q,et al.Ghostnet:More features from cheap operations[C].proceedings of the Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.2020:1580-1589.
[13] Stratosphere.Stratosphere Laboratory Datasets [Z].2015.
[14] Wang W,Zhu M,Zeng X,et al.Malware traffic classification using convolutional neural network for representation learning[C].In2017 International conference on information networking(ICOIN).2017:712-717.
[15] Lopez-Martin M,Carro B,Sanchez-Esguevillas A.et al.Network traffic classifier with convolutional and recurrent neural networks for Internet of Things[J].IEEE Access,2017,5:18042-18050.
[16] He H Y,Yang Z G.Chen X N.PERT:Payload encoding representation from transformer for encrypted traffic classification[C].In Proceedings of the 2020 IEEE ITU Kaleidoscope:Industry-Driven Digital Transformation.2020:1-8.
[17] Liu C,He L,Xiong G,et al.Fs-net:A flow sequence network for encrypted traffic classification[C].In Proceedings of the IEEE INFOCOM 2019-IEEE Conference On Computer Communications.2019:1171-1179.
备注/Memo
收稿日期:2024-08-02
基金项目:四川省科技计划项目(2023YFG0292)