计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 220800120-7.doi: 10.11896/jsjkx.220800120
马继烨, 朱国胜, 卫操, 曾堉萱
MA Jiye, ZHU Guosheng, WEI Cao, ZENG Yuxuan
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。
中图分类号:
[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. |
|