通信学报2025，Vol.46Issue(1)：167-191,25.DOI:10.11959/j.issn.1000-436x.2025006
基于机器学习的加密流量分类研究综述
Survey of research on encrypted traffic classification based on machine learning
摘要
Abstract
Encrypted traffic classification was an important component of network management and security protection.However,the complexity and variability of the current network traffic environment rendered traditional classification methods largely ineffective.Machine learning,particularly deep learning,with its strong feature extraction capabilities,has been widely used in the field of encrypted traffic classification.To this end,a systematic review of the latest advance-ments in machine learning-driven encrypted traffic classification was provided.Firstly,the encrypted traffic classification work was roughly divided into three parts:data collection and processing,feature extraction and selection,and traffic classification and performance evaluation,which correspond to data acquisition,significant feature construction,and model application and validation in encrypted traffic classification.The content was further subdivided into seven stages:traffic collection,dataset construction,data preprocessing,feature extraction,feature selection,classification models,and performance evaluation.A comprehensive summary,synthesis,and analysis of these seven stages were then conducted.Finally,the challenges faced by current research were analyzed in detail,and the future research directions for encrypted traffic classification were prospected.关键词
流量分析/加密流量分类/机器学习/深度学习Key words
traffic analysis/encrypted traffic classification/machine learning/deep learning分类
信息技术与安全科学引用本文复制引用
付钰,刘涛涛,王坤,俞艺涵..基于机器学习的加密流量分类研究综述[J].通信学报,2025,46(1):167-191,25.基金项目
国家自然科学基金资助项目(No.62102422) （No.62102422）
河南省科技攻关基金资助项目(No.242102211070) The National Natural Science Foundation of China(No.62102422),Henan Province Key Science and Technol-ogy Research Projects of China(No.242102211070) （No.242102211070）
