An Effective Intrusion Detection Model Based on Random Forest and Neural Networks

Abstract:

This document explains and demonstrates how to prepare your camera-ready manuscript for Trans Tech Publications. The best is to read these instructions and follow the outline of this text. The text area for your manuscript must be 17 cm wide and 25 cm high (6.7 and 9.8 inches, resp.). Do not place any text outside this area. Use good quality, white paper of approximately 21 x 29 cm or 8 x 11 inches (please do not change the document setting from A4 to letter). Your manuscript will be reduced by approximately 20% by the publisher. Please keep this in mind when designing your figures and tables etc.Intrusion detection is a very important research domain in network security. Current intrusion detection systems (IDS) especially NIDS (Network Intrusion Detection System) examine all data features to detect intrusions. Also, many machine learning and data mining methods are utilized to fulfill intrusion detection tasks. This paper proposes an effective intrusion detection model that is computationally efficient and effective based on Random Forest based feature selection approach and Neural Networks (NN) model. We firstly utilize random forest method to select the most important features to eliminate the insignificant and/or useless inputs leads to a simplification of the problem, in order to faster and more accurate detection; Secondly, classic NN model is used to learn and detect intrusions using the selected important features. Experimental results on the well-known KDD 1999 dataset demonstrate the proposed hybrid model is actually effective.

• Periodical: Advanced Materials Research (Volume 267)
• Pages: 308-313
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.267.308
• Online since: June 2011
• Authors: Shao Hong Zhong, Hua Jun Huang, Ai Bin Chen
• Keywords: Intrusion Detection, Neural Network (NN), Random Forest (RF)

References

[1] M. Bykova, S. Ostermann and B. Tjaden, Detecting network intrusions via a statistical analysis of network packet characteristics, in Proc. of the 33rd Southeastern Symp. on System Theory, Athens, OH. IEEE, (2001).

DOI: 10.1109/ssst.2001.918537

[2] C. Kruegel and F. Valeur, Stateful Intrusion Detection for High-Speed Networks, in Proc. of the IEEE Symposium on Research on Security and Privacy, pp.285-293, (2002).

DOI: 10.1109/secpri.2002.1004378

[3] T. Bass, Intrusion detection systems and multisensor data fusion, Communications of the ACM, 43 (4), p.99–105, (2000).

DOI: 10.1145/332051.332079

[4] Dash M., Liu H., & Motoda H, Consistency based feature selection, Proc. of the Fourth PAKDD 2000, Kyoto, Japan, 2000, p.98–109.

[5] H. Almuallim and T.G. Dietterich" Learning Boolean Concepts in the Presence of Many Irrelevant Features, Artificial Intelligence, vol. 69, nos. 1-2, 1994, pp.279-305.

DOI: 10.1016/0004-3702(94)90084-1

[6] H. Liu and L. Yu. Towards integrating feature selection algorithms for classification and clustering. IEEE Transactions on Knowledge and Data Engineering, 17(3): 1-12, (2005).

DOI: 10.1109/tkde.2005.66

[7] Dong Seong Kim, Sang Min Lee, and Jong Sou Park: Building Lightweight Intrusion Detection System Based on Random Forest. ISNN 2006, LNCS 3973, pp.224-230, (2006).

DOI: 10.1007/11760191_33

[8] Breiman, L.: Random forest. Machine Learning 45(1) (2001) 5–32.

[9] Duda, R. O., Hart, P. E., Stork, D. G.: Pattern Classification. 2nd edn. John Wiley & Sons, Inc. (2001).

[10] Hyvaerinen. A. Karhunen. J & Oja. E.: Independent Component Analysis. John Wiley, New York (2001).

[11] Introduction to Backpropagation Neural Networks. http: /cortex. snowcron. com/neural_networks. htm.

[12] Dagupta. D, Gonzalez. F: An immunity-based technique to characterize intrusions in computer networks, IEEE Transactions on Evolutionary Computation (2002) 28-291.

DOI: 10.1109/tevc.2002.1011541

[13] Weka Machine Learning Project, http: /www. cs. waikato. ac. nz/~ml.