Privacy Preserving Classification Based on Perturbation for Network Traffic
Network traffic classification is important to many network applications. Machine learning is regarded as one of the most effective technique to classify network traffic. In this paper, we adopt the fast correlation-based filter algorithm to filter redundant attributes contained in network traffic. The attributes selected by this algorithm help to reduce the classification complexity and achieve high classification accuracy. Since the traffic attributes contain a large amount of users’ behavior information, the privacy of user may be revealed and illegally used by malicious users. So it’s demanding to classify traffic with certain segment of frames which encloses privacy-related information being protected. After classification, the results do not disclose privacy information, while may still be used for data analysis. Therefore, we propose a random perturbation algorithm based on relationship among different data attributes’ orders, which protects their privacy, thus ensures data security during classification. The experiment results demonstrate that data perturbed by our algorithm is classified with high accuracy rate and data utility.
KeywordsNetwork traffic classification Privacy preserving Machine learning
This work was done under the support of Research Initiative Grant of Australian Research Council Discovery Projects funding DP150104871, Beijing Natural Science Foundation Grant No. 4172045 and National Science Foundation of China Grant No. 61501025.
- 1.Guo, L., Shen, H.: Privacy-preserving internet traffic publication. In: IEEE Trustcom/BigDataSE/ISPA, pp. 884–891 (2017)Google Scholar
- 3.Madhukar, A., Williamson, C.: A longitudinal study of P2P traffic classification. In: 14th IEEE International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, pp. 179–188 (2006)Google Scholar
- 6.Zander, S., Nguyen, T., Armitage, G.: Automated traffic classification and application identification using machine learning. In: IEEE Conference on Local Computer Networks, pp. 250–257 (2005)Google Scholar
- 7.Erman, J., Arlitt, M., Mahanti, A.: Traffic classification using clustering algorithms. In: Proceedings of the 2006 SIGCOMM Workshop on Mining Network Data, pp. 281–286 (2006)Google Scholar
- 9.Williams, N., Zander, S.: Evaluating machine learning algorithms for automated network application identification, Center for Advanced Internet Architectures Technical report (2006)Google Scholar
- 10.Li, W., Moore, A.W.: A machine learning approach for efficient traffic classification. In: 15th IEEE International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, pp. 310–317 (2007)Google Scholar
- 11.Deng, H., Yang, A.M.: P2P traffic classification method based on SVM. In: Computer Engineering and Applications (2006)Google Scholar
- 12.Aggarwal, C.C.: On k-anonymity and the curse of dimensionality. In: Proceedings of the 31st International Conference on Very Large Data Bases, pp. 901–909 (2005)Google Scholar
- 15.Moore, A.W., Zuev, D.: Discriminators for use in ow-based classification (2005)Google Scholar
- 16.Yu, L., Liu, H.: Feature selection for high-dimensional data: a fast correlation-based filter solution. In: 20th International Conference on Machine Learning, pp. 856–863 (2003)Google Scholar