A t-SNE based non linear dimension reduction for network intrusion detection
With the increased dependence on the internet for day to day activities, the need to keep the networks secure has become more vital. The quest of securing the computer systems and networks, from the users with destructive mindset, has resulted in the invention of surfeit devices and methods. One such method against whom the responsibility of discriminating between normal and harmful data, flowing on the network is, intrusion detection system (IDS). In this work an IDS model based on support vector machines is proposed. In order to enhance the detection capability of support vector machine based model for intrusion detection, and to eliminate the inherent problem of intrusion detection i.e, low accuracy of the system in detecting user to root and remote to local attacks, this paper proposes to use recent non-linear dimension reduction technique to enhance the discrimination of the data. Results demonstrate that t-SNE based dimension reduction improve the accuracy of SVM for network intrusion detection system. A comparison of the proposed system with the previous works has proven that this work has enhanced detection rate for almost all the attack groups.
KeywordsClassification Data visualization Dimension reduction Network intrusion detection NLDR PCA SVM t-SNE
Compliance with ethical standards
This work is a part of my Ph.D. project and as such I haven’t recieved any funding from any agency for this work. All the expenses for carrying out for this work have been made by the authors.
Conflict of interest
Authors have declared that no competing interests exist.
The authors would be happy to share the data with the intreseted researchers.
- 4.Liao Y, Vemuri VR (2005) Machine learning in intrusion detection. Enhancing Computer Security with Smart Technology, p 93Google Scholar
- 6.Dunteman GHC (1989) Principal components analysis. Sage, no. 69Google Scholar
- 7.Kruskal JB, Wish M (1978) Multidimensional scaling. Sage 11Google Scholar
- 9.Hinton GE, Roweis ST (2002) Stochastic neighbor embedding. In: Advances in neural information processing systems, pp 833–840Google Scholar
- 14.Hamid Y, Sugumaran M, Balasaraswathi V (2016) Ids using machine learning-current state of art and future directions. Br J Appl Sci Technol 15(3)Google Scholar
- 19.Hamid Y, Sugumaran M, Journaux L (2016) A fusion of feature extraction and feature selection technique for network intrusion detection. Int J Secur Appl 10(8):151–158Google Scholar
- 20.Xia Y-X, Shi Z-C, Hu Z-H (2009) An incremental svm forintrusion detection based on key feature selection. In: Intelligent information technology application, 2009. IITA2009. Third International Symposium on IEEE, vol. 3, pp 205–208Google Scholar
- 21.Xie L, Zhu D, Yang H (2009) Research on svm based network intrusion detection classification. In: Fuzzy systems and knowledge discovery, 2009. FSKD’09. Sixth International Conference on IEEEGoogle Scholar
- 22.Mukkamala S, Janoski G, Sung A (2002) Intrusion detection using neural networks and support vector machines. In: Neural networks, 2002. IJCNN’02. Proceedings of the 2002 International Joint Conference on IEEE, vol. 2, pp 1702–1707Google Scholar
- 23.Heba FE, Darwish A, Hassanien AE, Abraham A (2010) Principle components analysis and support vector machine based intrusion detection system. In: 2010 10th international conference on intelligent systems design and applications, pp 363–367Google Scholar
- 24.Labib K, Vemuri VR (2006) An application of principal component analysis to the detection and visualization of computer network attacks. In: Annales des télécommunications, vol. 61, no. 1-2. Springer, pp 218–234Google Scholar
- 25.Kuchimanchi GK, Phoha VV, Balagani KS, Gaddam SR (2004) Dimensionreduction using feature extraction methods for real-time misusedetection systems. In: Information Assurance Workshop, 2004. Proceedings from the Fifth Annual IEEE SMC, pp 195–202Google Scholar
- 26.Day CW (2006) Intrusion detection system using self-organizing clusters, uS Patent 7,017,186Google Scholar
- 27.Zanero S, Savaresi SM (2004) Unsupervised learning techniques for an intrusion detection system. In: Proceedings of the 2004 ACM symposium on Applied computing. ACM, pp 412–419Google Scholar
- 28.Day CW (2007) Intrusion detection system, US Patent 7,260,846Google Scholar
- 29.Dash SK, Rawat S, Pujari AK (2006) Lle on system calls for host based intrusion detection. In: 2006 international conference on computational intelligence and security, vol. 1, pp 609–612Google Scholar
- 32.Delion C, Journaux L, Payen A, Sautot L, Chevigny E, Curmi P (2015) Nldr methods for high dimensional nirs dataset: application to vineyard soils characterization. In: 23rd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN’15)Google Scholar
- 33.Payen A, Journaux L, Delion C, Sautot L, Faivre B (2015) Efficient unsupervised clustering for spatial bird population analysis along the loire river. In: 23rd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN’15)Google Scholar