计算机科学与探索2025，Vol.19Issue(5)：1230-1240,11.DOI:10.3778/j.issn.1673-9418.2407095
TCGCL:基于图对比学习的复杂网络流量分类算法
TCGCL:Complex Network Traffic Classification Algorithm Based on Graph Contrastive Learning
摘要
Abstract
Network traffic classification technology plays a crucial role in the field of network security.Modern network architecture is highly complex,and various abnormal situations will inevitably be encountered during network traffic transmission.To this end,this paper proposes a stability index to evaluate the algorithm's resistance to data anomaly inter-ference.In addition,a traffic classification algorithm TCGCL(traffic classification graph contrastive learning)is proposed based on graph contrastive learning.It can simultaneously extract the payload characteristics within network traffic and the connectivity relationship characteristics between network traffic,more comprehensively preserving the effective infor-mation of data.Based on this,through data augmentation technology,it simulates the abnormal state of network traffic,greatly improving the classification performance of the algorithm in the case of data anomalies.In addition,based on pro-tocol analysis techniques,this paper studies the construction of graph structured data in the process of traffic classification and proposes a high-quality and low dimensional attribute generation method.The experiment shows that compared with the baseline algorithm,TCGCL reduces the sample input dimension by about 80%with almost the same accuracy.For complex network communication environments,TCGCL conducts noise obfuscation on test samples and simulates abnor-mal traffic situations.The results show that TCGCL can still maintain high classification accuracy even under abnormal traffic conditions,and its stability index is significantly ahead of the baseline algorithm.关键词
流量分类/图神经网络/对比学习/协议分析Key words
traffic classification/graph neural networks/contrastive learning/protocol analysis分类
信息技术与安全科学引用本文复制引用
胡仲则,秦宏超,李振军,李艳辉,李荣华,王国仁..TCGCL:基于图对比学习的复杂网络流量分类算法[J].计算机科学与探索,2025,19(5):1230-1240,11.基金项目
国家重点研发计划(2021YFB3301301) （2021YFB3301301）
国家自然科学基金(U2241211,62072034,62202053) （U2241211,62072034,62202053）
重庆市教育委员会科学技术研究项目(KJQN202000707) （KJQN202000707）
重庆市自然科学基金(cstc2021jcyj-msxmX0859). This work was supported by the National Key Research and Development Program of China(2021YFB3301301),the National Natural Science Foundation of China(U2241211,62072034,62202053),the Science and Technology Research Program of Chongqing Munici-pal Education Commission(KJQN202000707),and the Natural Science Foundation of Chongqing(cstc2021jcyj-msxmX0859). （cstc2021jcyj-msxmX0859）
