计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 220800120-7.doi: 10.11896/jsjkx.220800120

• 网络&通信 • 上一篇    下一篇

一种噪声容忍的网络流量分类方法

马继烨, 朱国胜, 卫操, 曾堉萱   

  1. 湖北大学计算机与信息工程学院 武汉 430062
  • 发布日期:2023-11-09
  • 通讯作者: 朱国胜(zhuguosheng@hubu.edu.cn)
  • 作者简介:(majiyemjy@126.com)

Noise Tolerant Algorithm for Network Traffic Classification Method

MA Jiye, ZHU Guosheng, WEI Cao, ZENG Yuxuan   

  1. School of Computer and Information Engineering,Hubei University,Wuhan 430062,China
  • Published:2023-11-09
  • About author:ZHU Guosheng,born in 1972,Ph.D,professor,is a member of China Computer Federation.His main research interests include future networks and so on.

PDF (PC)

148

摘要： 针对传统基于机器学习的网络流量分类方法中样本标签的正确性会直接影响结果精度的问题,提出一种噪声容忍的网络流量分类方法。该方法基于深度残差网络的方法,首先,对网络流量数据进行归一化以及数据增强处理后映射成灰度图片,并对其样本标签进行不同程度的加噪;然后,基于Res2Net深度残差神经网络设计适用于网络流量噪声干扰下的维度模块,构造可以适用于流量标签噪声容忍的深度神经网络模型。基于公开数据集的实验结果表明,与传统的噪声容忍分类算法相比,基于改进的深度残差神经网络在不同噪声率下均提升了分类精度,并且在高噪声率下提升更为显著。

关键词: 噪声容忍, 深度学习, 残差学习, 流量分类, 标签噪声, 归一化

Abstract: Aiming at the problem that the correctness of the sample labels in the traditional machine learning-based network traffic classification method will directly affect the accuracy of the results,a noise-tolerant network traffic classification method is proposed,which is based on the deep residual network method.After normalization and data enhancement,the data is mapped into a grayscale image,and the sample labels are added to different degrees of noise.Then,based on the Res2Net deep residual neural network,a dimensional module suitable for the interference of network traffic noise is designed,and a deep neural network model suitable for traffic label noise tolerance is constructed.Experimental results on public datasets show that compared with the traditional noise-tolerant classification algorithm,the improved deep residual neural network improves the classification accuracy under different noise rates,and the improvement is more significant at high noise rates.

Key words: Noise tolerant, Deep learning, Residual learning, Network traffic classification, Label noise, Normalized

中图分类号: 

  • TP393
[1]ERMAN J,MAHANTI A,ARLITT M.Qrp05-4:Internet traffic identification using machine learning[C]//IEEE Globecom 2006.IEEE,2006:1-6.
[2]WANG Y,ZHOU H Y,FENG H,et al.A Network Traffic Classification Method Based on Deep Convolution Neural Network[J].Journal on Communications,2018,39(1):14-23.
[3]DONG S,XIA Y,PENG T.Traffic identification model based on generative adversarial deep convolutional network[J].Annals of Telecommunications,2022,77(9/10):573-587.
[4]XUE W L,YU J,GUO Z Q,et al.End-to-end encrypted traffic classification based on a feature fusion convolutional neural network[J].Computer Engineering and Application,2021,57(18):8.
[5]TANAKA D,IKAMI D,YAMASAKI T,et al.Joint optimization framework for learning with noisy labels[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:5552-5560.
[6]ZHANG C,BENGIO S,HARDT M,et al.Understanding deep learning(still) requires rethinking generalization[J].Communications of the ACM,2021,64(3):107-115.
[7]ARPIT D,JASTRZBSKI S,BALLAS N,et al.A closer look at memorization in deep networks[C]//International Conference on Machine Learning.PMLR,2017:233-242.
[8]XIAO T,XIA T,YANG Y,et al.Learning from massive noisy labeled data for image classification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:2691-2699.
[9]ZHENG S,WU P,GOSWAMI A,et al.Error-bounded correction of noisy labels[C]//International Conference on Machine Learning.PMLR,2020:11447-11457.
[10]HUANG J,QU L,JIA R,et al.O2u-net:A simple noisy labeldetection approach for deep neural networks[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:3326-3334.
[11]SHARMA K,DONMEZ P,LUO E,et al.Noiserank:Unsuper-vised label noise reduction with dependence models[C]//European Conference on Computer Vision.Cham:Springer,2020:737-753.
[12]CHAROENPHAKDEE N,LEE J,SUGIYAMA M.On sym-metric losses for learning from corrupted labels[C]//International Conference on Machine Learning.PMLR,2019:961-970.
[13]LI J,WONG Y,ZHAO Q,et al.Learning to learn from noisy labeled data[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:5051-5059.
[14]ALGAN G,ULUSOY I.Meta soft label generation for noisy labels[C]//2020 25th International Conference on Pattern Recognition(ICPR).IEEE,2021:7142-7148.
[15]HE K,ZHANG X,REN S,et al.Deep residual learning forimage recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778.
[16]SIMONYAN K,ZISSERMAN A.Very deep convolutional net-works for large-scale image recognition[J].arXiv:1409.1556,2014.
[17]NAIR V,HINTON G E.Rectified linear units improve re-stricted boltzmann machines[C]//ICML.2010.
[18]WANG Y,MA X,CHEN Z,et al.Symmetric cross entropy for robust learning with noisy labels[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:322-330.
[19]GAO S H,CHENG M M,ZHAO K,et al.Res2net:A newmulti-scale backbone architecture[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2019,43(2):652-662.
[20]LI W,CANINI M,MOORE A W,et al.Efficient applicationidentification and the temporal and spatial stability of classification schema[J].Computer Networks,2009,53(6):790-809.
[21]WANG F Y.Machine Learning in Network Traffic Classification[D].Chengdu:University of Electronic Science and Technology of China,2023.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发