Differential Preserving in XGBoost Model for Encrypted Traffic Classification
- Publisher:
- Institute of Electrical and Electronics Engineers (IEEE)
- Publication Type:
- Conference Proceeding
- Citation:
- Proceedings - 2022 International Conference on Networking and Network Applications, NaNA 2022, 2022, 00, pp. 220-225
- Issue Date:
- 2022-12-05
Closed Access
Filename | Description | Size | |||
---|---|---|---|---|---|
Differential Preserving in XGBoost Model for Encrypted Traffic Classification.pdf | Published version | 1.49 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
The classification of encrypted traffic is becoming ever more relevant in the field of network security management and cybersecurity. Most users are currently using encrypted traffic, which can easily lead to privacy threats, and attackers can identify user behavior through the information obtained. VPN encrypted tunnel is the most popular encrypted tunnel method at present. This paper proposes to use the XGBoost model to classify VPNs and Non-VPNs, normalizing the features extracted from encrypted traffic. Experiments are performed on the public dataset ISCX VPN-nonVPN, and the results show that the XGBoost model has an accuracy of 92.4%. To illustrate the advantages of this model, it is compared with the other 5 classification algorithms. At the same time, this paper applies differential privacy technology to the classification model of encrypted traffic and reduces privacy threats by obfuscating data features.
Please use this identifier to cite or link to this item: