CDBC: A novel data enhancement method based on improved between-class learning for darknet detection
With the development of the Internet, people have paid more attention to privacy protection, and privacy protection technology is widely used. However, it also breeds the darknet, which has become a tool that criminals can exploit, especially in the fields of economic crime and military intelligence...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2023-07-01
|
| Series: | Mathematical Biosciences and Engineering |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/mbe.2023670?viewType=HTML |
| _version_ | 1797749186097053696 |
|---|---|
| author | Binjie Song Yufei Chang Minxi Liao Yuanhang Wang Jixiang Chen Nianwang Wang |
| author_facet | Binjie Song Yufei Chang Minxi Liao Yuanhang Wang Jixiang Chen Nianwang Wang |
| author_sort | Binjie Song |
| collection | DOAJ |
| description | With the development of the Internet, people have paid more attention to privacy protection, and privacy protection technology is widely used. However, it also breeds the darknet, which has become a tool that criminals can exploit, especially in the fields of economic crime and military intelligence. The darknet detection is becoming increasingly important; however, the darknet traffic is seriously unbalanced. The detection is difficult and the accuracy of the detection methods needs to be improved. To overcome these problems, we first propose a novel learning method. The method is the Chebyshev distance based Between-class learning (CDBC), which can learn the spatial distribution of the darknet dataset, and generate "gap data". The gap data can be adopted to optimize the distribution boundaries of the dataset. Second, a novel darknet traffic detection method is proposed. We test the proposed method on the ISCXTor 2016 dataset and the CIC-Darknet 2020 dataset, and the results show that CDBC can help more than 10 existing methods improve accuracy, even up to 99.99%. Compared with other sampling methods, CDBC can also help the classifiers achieve higher recall. |
| first_indexed | 2024-03-12T16:16:34Z |
| format | Article |
| id | doaj.art-91d4376834e144e294078675a6ab800e |
| institution | Directory Open Access Journal |
| issn | 1551-0018 |
| language | English |
| last_indexed | 2024-03-12T16:16:34Z |
| publishDate | 2023-07-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | Mathematical Biosciences and Engineering |
| spelling | doaj.art-91d4376834e144e294078675a6ab800e2023-08-09T01:23:07ZengAIMS PressMathematical Biosciences and Engineering1551-00182023-07-01208149591497710.3934/mbe.2023670CDBC: A novel data enhancement method based on improved between-class learning for darknet detectionBinjie Song0Yufei Chang 1Minxi Liao2Yuanhang Wang 3Jixiang Chen4Nianwang Wang51. Academy of A&AD, Zhengzhou 450000, China2. South China University of Technology, Guangzhou 511400, China3. State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou 450001, China1. Academy of A&AD, Zhengzhou 450000, China2. South China University of Technology, Guangzhou 511400, China1. Academy of A&AD, Zhengzhou 450000, ChinaWith the development of the Internet, people have paid more attention to privacy protection, and privacy protection technology is widely used. However, it also breeds the darknet, which has become a tool that criminals can exploit, especially in the fields of economic crime and military intelligence. The darknet detection is becoming increasingly important; however, the darknet traffic is seriously unbalanced. The detection is difficult and the accuracy of the detection methods needs to be improved. To overcome these problems, we first propose a novel learning method. The method is the Chebyshev distance based Between-class learning (CDBC), which can learn the spatial distribution of the darknet dataset, and generate "gap data". The gap data can be adopted to optimize the distribution boundaries of the dataset. Second, a novel darknet traffic detection method is proposed. We test the proposed method on the ISCXTor 2016 dataset and the CIC-Darknet 2020 dataset, and the results show that CDBC can help more than 10 existing methods improve accuracy, even up to 99.99%. Compared with other sampling methods, CDBC can also help the classifiers achieve higher recall.https://www.aimspress.com/article/doi/10.3934/mbe.2023670?viewType=HTMLbetween-class learningdarknetdetectiontraffic classification |
| spellingShingle | Binjie Song Yufei Chang Minxi Liao Yuanhang Wang Jixiang Chen Nianwang Wang CDBC: A novel data enhancement method based on improved between-class learning for darknet detection Mathematical Biosciences and Engineering between-class learning darknet detection traffic classification |
| title | CDBC: A novel data enhancement method based on improved between-class learning for darknet detection |
| title_full | CDBC: A novel data enhancement method based on improved between-class learning for darknet detection |
| title_fullStr | CDBC: A novel data enhancement method based on improved between-class learning for darknet detection |
| title_full_unstemmed | CDBC: A novel data enhancement method based on improved between-class learning for darknet detection |
| title_short | CDBC: A novel data enhancement method based on improved between-class learning for darknet detection |
| title_sort | cdbc a novel data enhancement method based on improved between class learning for darknet detection |
| topic | between-class learning darknet detection traffic classification |
| url | https://www.aimspress.com/article/doi/10.3934/mbe.2023670?viewType=HTML |
| work_keys_str_mv | AT binjiesong cdbcanoveldataenhancementmethodbasedonimprovedbetweenclasslearningfordarknetdetection AT yufeichang cdbcanoveldataenhancementmethodbasedonimprovedbetweenclasslearningfordarknetdetection AT minxiliao cdbcanoveldataenhancementmethodbasedonimprovedbetweenclasslearningfordarknetdetection AT yuanhangwang cdbcanoveldataenhancementmethodbasedonimprovedbetweenclasslearningfordarknetdetection AT jixiangchen cdbcanoveldataenhancementmethodbasedonimprovedbetweenclasslearningfordarknetdetection AT nianwangwang cdbcanoveldataenhancementmethodbasedonimprovedbetweenclasslearningfordarknetdetection |