An encrypted traffic identification method based on multi-scale feature fusion
As data privacy issues become more and more sensitive, increasing numbers of websites usually encrypt traffic when transmitting it. This method can largely protect privacy, but it also brings a huge challenge. Aiming at the problem that encrypted traffic classification makes it difficult to obtain a...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2024-03-01
|
Series: | Array |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2590005624000043 |
_version_ | 1797266429712531456 |
---|---|
author | Peng Zhu Gang Wang Jingheng He Yueli Dong Yu Chang |
author_facet | Peng Zhu Gang Wang Jingheng He Yueli Dong Yu Chang |
author_sort | Peng Zhu |
collection | DOAJ |
description | As data privacy issues become more and more sensitive, increasing numbers of websites usually encrypt traffic when transmitting it. This method can largely protect privacy, but it also brings a huge challenge. Aiming at the problem that encrypted traffic classification makes it difficult to obtain a global optimal solution, this paper proposes an encrypted traffic identification model called the ET-BERT and 1D-CNN fusion network (BCFNet), based on multi-scale feature fusion. This method combines feature learning with classification tasks, unified into an end-to-end model. The local features of encrypted traffic extracted based on the improved Inception one-dimensional convolutional neural network structure are fused with the global features extracted by the ET-BERT model. The one-dimensional convolutional neural network is more suitable for the encrypted traffic of a one-dimensional sequence than the commonly used two-dimensional convolutional neural network. The proposed model can learn the nonlinear relationship between the input data and the expected label and obtain the global optimal solution with a greater probability. This paper verifies the ISCX VPN-nonVPN dataset and compares the results of the BCFNet model with the other five baseline models on accuracy, precision, recall, and F1 indicators. The experimental results demonstrate that the BCFNet model has a greater overall effect than the other five models. Its accuracy can reach 98.88%. |
first_indexed | 2024-03-07T21:27:49Z |
format | Article |
id | doaj.art-71aff49f37014a4eb124cc6b0bc0b335 |
institution | Directory Open Access Journal |
issn | 2590-0056 |
language | English |
last_indexed | 2024-04-25T01:00:33Z |
publishDate | 2024-03-01 |
publisher | Elsevier |
record_format | Article |
series | Array |
spelling | doaj.art-71aff49f37014a4eb124cc6b0bc0b3352024-03-11T04:11:05ZengElsevierArray2590-00562024-03-0121100338An encrypted traffic identification method based on multi-scale feature fusionPeng Zhu0Gang Wang1Jingheng He2Yueli Dong3Yu Chang4College of Data Science and Application, Inner Mongolia University of Technology, Hohhot, ChinaCollege of Data Science and Application, Inner Mongolia University of Technology, Hohhot, China; Corresponding author.College of Data Science and Application, Inner Mongolia University of Technology, Hohhot, ChinaOrdos Institute of Applied Technology Big Aircraft College, Ordos, ChinaCollege of Data Science and Application, Inner Mongolia University of Technology, Hohhot, ChinaAs data privacy issues become more and more sensitive, increasing numbers of websites usually encrypt traffic when transmitting it. This method can largely protect privacy, but it also brings a huge challenge. Aiming at the problem that encrypted traffic classification makes it difficult to obtain a global optimal solution, this paper proposes an encrypted traffic identification model called the ET-BERT and 1D-CNN fusion network (BCFNet), based on multi-scale feature fusion. This method combines feature learning with classification tasks, unified into an end-to-end model. The local features of encrypted traffic extracted based on the improved Inception one-dimensional convolutional neural network structure are fused with the global features extracted by the ET-BERT model. The one-dimensional convolutional neural network is more suitable for the encrypted traffic of a one-dimensional sequence than the commonly used two-dimensional convolutional neural network. The proposed model can learn the nonlinear relationship between the input data and the expected label and obtain the global optimal solution with a greater probability. This paper verifies the ISCX VPN-nonVPN dataset and compares the results of the BCFNet model with the other five baseline models on accuracy, precision, recall, and F1 indicators. The experimental results demonstrate that the BCFNet model has a greater overall effect than the other five models. Its accuracy can reach 98.88%.http://www.sciencedirect.com/science/article/pii/S2590005624000043Encrypted traffic classificationGlobal optimal solutionMulti-scale feature fusionET-BERTOne-dimensional convolutional neural network |
spellingShingle | Peng Zhu Gang Wang Jingheng He Yueli Dong Yu Chang An encrypted traffic identification method based on multi-scale feature fusion Array Encrypted traffic classification Global optimal solution Multi-scale feature fusion ET-BERT One-dimensional convolutional neural network |
title | An encrypted traffic identification method based on multi-scale feature fusion |
title_full | An encrypted traffic identification method based on multi-scale feature fusion |
title_fullStr | An encrypted traffic identification method based on multi-scale feature fusion |
title_full_unstemmed | An encrypted traffic identification method based on multi-scale feature fusion |
title_short | An encrypted traffic identification method based on multi-scale feature fusion |
title_sort | encrypted traffic identification method based on multi scale feature fusion |
topic | Encrypted traffic classification Global optimal solution Multi-scale feature fusion ET-BERT One-dimensional convolutional neural network |
url | http://www.sciencedirect.com/science/article/pii/S2590005624000043 |
work_keys_str_mv | AT pengzhu anencryptedtrafficidentificationmethodbasedonmultiscalefeaturefusion AT gangwang anencryptedtrafficidentificationmethodbasedonmultiscalefeaturefusion AT jinghenghe anencryptedtrafficidentificationmethodbasedonmultiscalefeaturefusion AT yuelidong anencryptedtrafficidentificationmethodbasedonmultiscalefeaturefusion AT yuchang anencryptedtrafficidentificationmethodbasedonmultiscalefeaturefusion AT pengzhu encryptedtrafficidentificationmethodbasedonmultiscalefeaturefusion AT gangwang encryptedtrafficidentificationmethodbasedonmultiscalefeaturefusion AT jinghenghe encryptedtrafficidentificationmethodbasedonmultiscalefeaturefusion AT yuelidong encryptedtrafficidentificationmethodbasedonmultiscalefeaturefusion AT yuchang encryptedtrafficidentificationmethodbasedonmultiscalefeaturefusion |