工业互联网流量分析技术综述
Survey of industrial Internet traffic analysis technology
刘奇旭 1肖聚鑫 1谭耀康 1王承淳 1黄昊 1张方娇 2尹捷 2刘玉岭1
作者信息
- 1. 中国科学院信息工程研究所,北京 100085;中国科学院大学网络空间安全学院,北京 100049
- 2. 中国科学院信息工程研究所,北京 100085
- 折叠
摘要
为了深入理解流量分析技术在工业互联网中的应用,基于流量分析的5个主要步骤阐述了工业互联网区别于传统互联网的独特性.同时,通过调研大量相关研究工作,总结了流量预测、协议识别与逆向、工业资产指纹识别、入侵检测、加密流量识别和漏洞挖掘6个主流研究任务,并根据任务性质将其分类为面向服务质量提高和面向安全能力提升的2类应用,充分挖掘了工业互联网中的流量分析技术应用场景.最后,针对流量分析未来进一步应用于工业互联网所面临的挑战进行了讨论,并展望了潜在的研究方向.
Abstract
To gain an in-depth awareness of the application of traffic analysis technology in the industrial Internet,the dif-ferences between the industrial Internet and the traditional Internet through the five core traffic analysis processes were il-lustrated.By reviewing a large number of related papers,the application of six popular were summarized in the industrial Internet,such as traffic prediction,protocol identification and reverse engineering,industrial asset fingerprinting,intru-sion detection,encrypted traffic identification and vulnerability mining.Depending on the nature of the task,traffic analysis technology was classified into two types of applications,such as service quality enhancement and security capa-bility development,allowing to thoroughly explore the application scenarios of traffic analysis technology in the indus-trial Internet.Finally,the challenges associated with future traffic analysis applications in the industrial Internet were ex-amined,as well as potential development possibilities.
关键词
工业互联网/工业控制系统/流量分析/机器学习Key words
industrial Internet/industrial control system/traffic analysis/machine learning引用本文复制引用
基金项目
中国科学院青年创新促进会项目()
国家电网科技基金(SG270000YXJS2311060)
中国科学院网络测评技术重点实验室和网络安全防护技术北京市重点实验室项目()
出版年
2024
国家科技期刊平台
NSTL
万方数据