Research on QoS Classification of Network Encrypted Traffic Behavior Based on Machine Learning
In recent years, privacy awareness is concerned due to many Internet services have chosen to use encrypted agreements. In order to improve the quality of service (QoS), the network encrypted traffic behaviors are classified based on machine learning discussed in this paper. However, the traditional...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-06-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/10/12/1376 |
_version_ | 1797530849150763008 |
---|---|
author | Yung-Fa Huang Chuan-Bi Lin Chien-Min Chung Ching-Mu Chen |
author_facet | Yung-Fa Huang Chuan-Bi Lin Chien-Min Chung Ching-Mu Chen |
author_sort | Yung-Fa Huang |
collection | DOAJ |
description | In recent years, privacy awareness is concerned due to many Internet services have chosen to use encrypted agreements. In order to improve the quality of service (QoS), the network encrypted traffic behaviors are classified based on machine learning discussed in this paper. However, the traditional traffic classification methods, such as IP/ASN (Autonomous System Number) analysis, Port-based and deep packet inspection, etc., can classify traffic behavior, but cannot effectively handle encrypted traffic. Thus, this paper proposed a hybrid traffic classification (HTC) method based on machine learning and combined with IP/ASN analysis with deep packet inspection. Moreover, the majority voting method was also used to quickly classify different QoS traffic accurately. Experimental results show that the proposed HTC method can effectively classify different encrypted traffic. The classification accuracy can be further improved by 10% with majority voting as K = 13. Especially when the networking data are using the same protocol, the proposed HTC can effectively classify the traffic data with different behaviors with the differentiated services code point (DSCP) mark. |
first_indexed | 2024-03-10T10:35:51Z |
format | Article |
id | doaj.art-224fa94bcb0e40e7bc0ebf2daf22b010 |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-10T10:35:51Z |
publishDate | 2021-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-224fa94bcb0e40e7bc0ebf2daf22b0102023-11-21T23:18:26ZengMDPI AGElectronics2079-92922021-06-011012137610.3390/electronics10121376Research on QoS Classification of Network Encrypted Traffic Behavior Based on Machine LearningYung-Fa Huang0Chuan-Bi Lin1Chien-Min Chung2Ching-Mu Chen3Department of Information and Communication Engineering, Chaoyang University of Technology, Taichung 413310, TaiwanDepartment of Information and Communication Engineering, Chaoyang University of Technology, Taichung 413310, TaiwanDepartment of Information and Communication Engineering, Chaoyang University of Technology, Taichung 413310, TaiwanSchool of Engineering, Chung Chou University of Science and Technology, Changhua County 51003, TaiwanIn recent years, privacy awareness is concerned due to many Internet services have chosen to use encrypted agreements. In order to improve the quality of service (QoS), the network encrypted traffic behaviors are classified based on machine learning discussed in this paper. However, the traditional traffic classification methods, such as IP/ASN (Autonomous System Number) analysis, Port-based and deep packet inspection, etc., can classify traffic behavior, but cannot effectively handle encrypted traffic. Thus, this paper proposed a hybrid traffic classification (HTC) method based on machine learning and combined with IP/ASN analysis with deep packet inspection. Moreover, the majority voting method was also used to quickly classify different QoS traffic accurately. Experimental results show that the proposed HTC method can effectively classify different encrypted traffic. The classification accuracy can be further improved by 10% with majority voting as K = 13. Especially when the networking data are using the same protocol, the proposed HTC can effectively classify the traffic data with different behaviors with the differentiated services code point (DSCP) mark.https://www.mdpi.com/2079-9292/10/12/1376quality of servicemachine learningdifferentiated servicetraffic classification |
spellingShingle | Yung-Fa Huang Chuan-Bi Lin Chien-Min Chung Ching-Mu Chen Research on QoS Classification of Network Encrypted Traffic Behavior Based on Machine Learning Electronics quality of service machine learning differentiated service traffic classification |
title | Research on QoS Classification of Network Encrypted Traffic Behavior Based on Machine Learning |
title_full | Research on QoS Classification of Network Encrypted Traffic Behavior Based on Machine Learning |
title_fullStr | Research on QoS Classification of Network Encrypted Traffic Behavior Based on Machine Learning |
title_full_unstemmed | Research on QoS Classification of Network Encrypted Traffic Behavior Based on Machine Learning |
title_short | Research on QoS Classification of Network Encrypted Traffic Behavior Based on Machine Learning |
title_sort | research on qos classification of network encrypted traffic behavior based on machine learning |
topic | quality of service machine learning differentiated service traffic classification |
url | https://www.mdpi.com/2079-9292/10/12/1376 |
work_keys_str_mv | AT yungfahuang researchonqosclassificationofnetworkencryptedtrafficbehaviorbasedonmachinelearning AT chuanbilin researchonqosclassificationofnetworkencryptedtrafficbehaviorbasedonmachinelearning AT chienminchung researchonqosclassificationofnetworkencryptedtrafficbehaviorbasedonmachinelearning AT chingmuchen researchonqosclassificationofnetworkencryptedtrafficbehaviorbasedonmachinelearning |