Condensation of Data and Knowledge for Network Traffic Classification: Techniques, Applications, and Open Issues

The accurate and efficient classification of network traffic, including malicious traffic, is essential for effective network management, cybersecurity, and resource optimization. However, traffic classification methods in modern, complex, and dynamic networks face significant challenges, particular...

Full description

Saved in:
Bibliographic Details
Main Authors: Changqing Zhao, Ling Xia Liao, Guomin Chen, Han-Chieh Chao
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/8/2368
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713311861440512
author Changqing Zhao
Ling Xia Liao
Guomin Chen
Han-Chieh Chao
author_facet Changqing Zhao
Ling Xia Liao
Guomin Chen
Han-Chieh Chao
author_sort Changqing Zhao
collection DOAJ
description The accurate and efficient classification of network traffic, including malicious traffic, is essential for effective network management, cybersecurity, and resource optimization. However, traffic classification methods in modern, complex, and dynamic networks face significant challenges, particularly at the network edge, where resources are limited and issues such as privacy concerns and concept drift arise. Condensation techniques offer a solution by reducing the data size, simplifying complex models, and transferring knowledge from traffic data. This paper explores data and knowledge condensation methods—such as coreset selection, data compression, knowledge distillation, and dataset distillation—within the context of traffic classification tasks. It clarifies the relationship between these techniques and network traffic classification, introducing each method and its typical applications. This paper also outlines potential scenarios for applying each condensation technique, highlighting the associated challenges and open research issues. To the best of our knowledge, this is the first comprehensive summary of condensation techniques specifically tailored for network traffic classification tasks.
format Article
id doaj-art-9bb9c215f5f441a4a25685ea44e42cf5
institution DOAJ
issn 1424-8220
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-9bb9c215f5f441a4a25685ea44e42cf52025-08-20T03:13:59ZengMDPI AGSensors1424-82202025-04-01258236810.3390/s25082368Condensation of Data and Knowledge for Network Traffic Classification: Techniques, Applications, and Open IssuesChangqing Zhao0Ling Xia Liao1Guomin Chen2Han-Chieh Chao3School of Electronic Information and Automation, Guilin University of Aerospace Technology, Guilin 541004, ChinaSchool of Electronic Information and Automation, Guilin University of Aerospace Technology, Guilin 541004, ChinaSchool of Management, Guilin University of Aerospace Technology, Guilin 541004, ChinaDepartment of Applied Informatics, Fo Guang University, Yilan 36247, TaiwanThe accurate and efficient classification of network traffic, including malicious traffic, is essential for effective network management, cybersecurity, and resource optimization. However, traffic classification methods in modern, complex, and dynamic networks face significant challenges, particularly at the network edge, where resources are limited and issues such as privacy concerns and concept drift arise. Condensation techniques offer a solution by reducing the data size, simplifying complex models, and transferring knowledge from traffic data. This paper explores data and knowledge condensation methods—such as coreset selection, data compression, knowledge distillation, and dataset distillation—within the context of traffic classification tasks. It clarifies the relationship between these techniques and network traffic classification, introducing each method and its typical applications. This paper also outlines potential scenarios for applying each condensation technique, highlighting the associated challenges and open research issues. To the best of our knowledge, this is the first comprehensive summary of condensation techniques specifically tailored for network traffic classification tasks.https://www.mdpi.com/1424-8220/25/8/2368network traffic classificationconcept driftknowledge transferringmodel distillationdataset distillation
spellingShingle Changqing Zhao
Ling Xia Liao
Guomin Chen
Han-Chieh Chao
Condensation of Data and Knowledge for Network Traffic Classification: Techniques, Applications, and Open Issues
Sensors
network traffic classification
concept drift
knowledge transferring
model distillation
dataset distillation
title Condensation of Data and Knowledge for Network Traffic Classification: Techniques, Applications, and Open Issues
title_full Condensation of Data and Knowledge for Network Traffic Classification: Techniques, Applications, and Open Issues
title_fullStr Condensation of Data and Knowledge for Network Traffic Classification: Techniques, Applications, and Open Issues
title_full_unstemmed Condensation of Data and Knowledge for Network Traffic Classification: Techniques, Applications, and Open Issues
title_short Condensation of Data and Knowledge for Network Traffic Classification: Techniques, Applications, and Open Issues
title_sort condensation of data and knowledge for network traffic classification techniques applications and open issues
topic network traffic classification
concept drift
knowledge transferring
model distillation
dataset distillation
url https://www.mdpi.com/1424-8220/25/8/2368
work_keys_str_mv AT changqingzhao condensationofdataandknowledgefornetworktrafficclassificationtechniquesapplicationsandopenissues
AT lingxialiao condensationofdataandknowledgefornetworktrafficclassificationtechniquesapplicationsandopenissues
AT guominchen condensationofdataandknowledgefornetworktrafficclassificationtechniquesapplicationsandopenissues
AT hanchiehchao condensationofdataandknowledgefornetworktrafficclassificationtechniquesapplicationsandopenissues