Data Augmentation-Based Enhancement for Efficient Network Traffic Classification
The necessity of Network traffic classification is becoming increasingly significant as users’ applications and devices become more diverse and prevalent. As encryption becomes the norm for security reasons, the traffic classification problem is not easily solved. In this work, we provide...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10819380/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841542545195139072 |
|---|---|
| author | Chang-Yui Shin Yang-Seo Choi Myung-Sup Kim |
| author_facet | Chang-Yui Shin Yang-Seo Choi Myung-Sup Kim |
| author_sort | Chang-Yui Shin |
| collection | DOAJ |
| description | The necessity of Network traffic classification is becoming increasingly significant as users’ applications and devices become more diverse and prevalent. As encryption becomes the norm for security reasons, the traffic classification problem is not easily solved. In this work, we provide an inductive counterevidence to the vague belief that deep learning models can perform well and outperform tree-based machine learning models in all aspects across domains, especially in the network traffic classification domain. We address the problem of finding an efficient encrypted traffic classification method in resource-constrained situations in the network traffic classification domain by limiting the scope of our research. Using the first packet, we converted packet headers and encrypted partial payloads into tabular data through a standardized format. We used them as the same inputs for lightweight deep learning and tree-based machine learning models, analyzed their performance, and identified efficient models. Next, we improved the performance of the previously selected efficient traffic classifier through data augmentation methods. Augmentation was performed to a degree that did not significantly damage the original data distribution so that the augmented dataset’s class distribution did not interfere with model learning. We applied two fundamentally contrasting methods to augment traffic data, depending on whether the basis of data augmentation is individual data or the entire data. Data augmentation increased the accuracy of the machine learning model by 0.26%, which complemented the machine learning model’s performance in network traffic classification and made the machine learning model outperform the lightweight deep learning model. |
| format | Article |
| id | doaj-art-505e947e959f430896e59ee85d2d35ee |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-505e947e959f430896e59ee85d2d35ee2025-01-14T00:02:33ZengIEEEIEEE Access2169-35362025-01-01136006602810.1109/ACCESS.2024.352500010819380Data Augmentation-Based Enhancement for Efficient Network Traffic ClassificationChang-Yui Shin0https://orcid.org/0000-0002-8410-0177Yang-Seo Choi1Myung-Sup Kim2https://orcid.org/0000-0002-3809-2057C4ISR System Development Quality Team, Defense Agency for Technology and Quality, Daejeon, South KoreaDepartment of Cyber Security Research Division, Electronics and Telecommunications Research Institute, Daejeon, South KoreaDepartment of Computer Convergence Software, Korea University, Sejong, South KoreaThe necessity of Network traffic classification is becoming increasingly significant as users’ applications and devices become more diverse and prevalent. As encryption becomes the norm for security reasons, the traffic classification problem is not easily solved. In this work, we provide an inductive counterevidence to the vague belief that deep learning models can perform well and outperform tree-based machine learning models in all aspects across domains, especially in the network traffic classification domain. We address the problem of finding an efficient encrypted traffic classification method in resource-constrained situations in the network traffic classification domain by limiting the scope of our research. Using the first packet, we converted packet headers and encrypted partial payloads into tabular data through a standardized format. We used them as the same inputs for lightweight deep learning and tree-based machine learning models, analyzed their performance, and identified efficient models. Next, we improved the performance of the previously selected efficient traffic classifier through data augmentation methods. Augmentation was performed to a degree that did not significantly damage the original data distribution so that the augmented dataset’s class distribution did not interfere with model learning. We applied two fundamentally contrasting methods to augment traffic data, depending on whether the basis of data augmentation is individual data or the entire data. Data augmentation increased the accuracy of the machine learning model by 0.26%, which complemented the machine learning model’s performance in network traffic classification and made the machine learning model outperform the lightweight deep learning model.https://ieeexplore.ieee.org/document/10819380/Network traffic classificationdata augmentationgenerative adversarial networkstabularrobustness |
| spellingShingle | Chang-Yui Shin Yang-Seo Choi Myung-Sup Kim Data Augmentation-Based Enhancement for Efficient Network Traffic Classification IEEE Access Network traffic classification data augmentation generative adversarial networks tabular robustness |
| title | Data Augmentation-Based Enhancement for Efficient Network Traffic Classification |
| title_full | Data Augmentation-Based Enhancement for Efficient Network Traffic Classification |
| title_fullStr | Data Augmentation-Based Enhancement for Efficient Network Traffic Classification |
| title_full_unstemmed | Data Augmentation-Based Enhancement for Efficient Network Traffic Classification |
| title_short | Data Augmentation-Based Enhancement for Efficient Network Traffic Classification |
| title_sort | data augmentation based enhancement for efficient network traffic classification |
| topic | Network traffic classification data augmentation generative adversarial networks tabular robustness |
| url | https://ieeexplore.ieee.org/document/10819380/ |
| work_keys_str_mv | AT changyuishin dataaugmentationbasedenhancementforefficientnetworktrafficclassification AT yangseochoi dataaugmentationbasedenhancementforefficientnetworktrafficclassification AT myungsupkim dataaugmentationbasedenhancementforefficientnetworktrafficclassification |