Performance Analysis of Some Neural Network Algorithms using NSL-KDD Dataset

International Journal of Computer Trends and Technology (IJCTT)          
© 2017 by IJCTT Journal
Volume-50 Number-1
Year of Publication : 2017
Authors : Jamal Hussain, Aishwarya Mishra


Jamal Hussain, Aishwarya Mishra "Performance Analysis of Some Neural Network Algorithms using NSL-KDD Dataset". International Journal of Computer Trends and Technology (IJCTT) V50(1):43-49, August 2017. ISSN:2231-2803. Published by Seventh Sense Research Group.

Abstract -
Consequent upon the growth of Internet and multifarious technologies including smart devices and their massive use and operations on Internet platform not only caused serious threats on security but also abnormal traffic detection. A number of assorted attacks on Internet seriously affect the systems. This not only leads to deteriorate the performance in the computer but also malfunctioning of the system. Vast growth of data in various areas due to adoption of computer technologies precipitated to anomalies. Thus, in such an alarming situation, anomalous traffic detection became a major concern of the security. Intrusion detection system is one of the redressed techniques that can be employed to determine the system security which detects the intrusion. In this paper performance of NSL-KDD dataset has been evaluated using LVQ, RBFN, DECR_RBFN, EVRBFN, MLP_BP, SONN networks of ANN showing the results that constitute binary class. Based on various performance measures analytical results were derived.

[1] R. R. Reddy, B. Kavya and Y. Ramadevi,Y..A survey on SVM for Intrusion Detection. International Journal of Computer Application. 98(19): 38-43, 2014.
[2] B. Ingre and A. Yadav. Performance Analysis of NSL-KDD dataset using ANN. Signal Processing and Communication Engineering Systems (SPACES).92-96, 2015.
[3] G. Schaffer. Building a cheap and powerful intrusion detection system. Computer world. 2007 Available
[4] R.A. Kemmerer and G. Vigna. Intrusion detection: A brief history and overview. Security & Privacy.27-30, 2002.
[5] K.K. Frederick. Network Intrusion Detection Signature. 2001. Available http://online. Securityfocus. com/infocus/1524.
[6] S. Kumar and A. Yadav. Increasing performance of intrusion detection system. IEEE Int. conf. on Advanced communication control and computing technology.546-550,2014
[7] S. Ranshous, S. Shen, D. Koutra, C. Faloutsos and N.F. Samatova. Anomaly Detection in Dynamic Networks: A Survey. WIREs Computational Statistics.7.223-247, 2014.
[8] J. Rejchrt. Network Anomaly Detection–Survey Evaluation. 2014. Available https://labs. Members/jan_rejchrt/network-anomaly-detection-2013-survey evaluation.
[9] A.A. Sayer, S. N. Pawar and V. Mane. A Review of Intrusion Detection System in Computer Network, International Journal of Computer Science and Mobile Computing, 3(2): 700-703, 2014.
[10] A. Shrivastava, M. Baghel and H. Gupta, H. A Review of Intrusion Detection by Soft Computing and Data Mining Approach, International Journal of Advanced Computer Research, 3(12): 224-228, 2013.
[11] J. Wang and Y. Yu.. Research on Hybrid Neural Network in Intrusion Detection System, World Academy of Science, Engineering and Technology, 7(4): 481-485,2013.
[12] R. R. Panko. . Corporate Computer and Network Security, 2nd ed., New Delhi, 2012.
[13] P. K. Singh, A. K. Vatsa, R. Sharma and P. Tyagi. Taxonomy Based Intrusion Attacks and Detection Management Scheme in Peer to Peer Network, International Journal of Network Security & Its Applications (IJNSA), 4 (5): 167-179, 2012.
[14] T. Vamsidhar, A. Reddyboina and V. Rayala. Intrusion Detection System for Web Application with attack classification, Journal of Global Research in Computer Science, 3(12): 44 -50, 2012.
[15] D. P. Vinchurkar and A. Reshamwala. A Review of Intrusion Detection System Using Neural Network and Machine Learning Technique, International Journal of Engineering Science and Innovative Technology, 1(2): 54-63, 2012.
[16] R. Somer. Viable Network Intrusion Detection: Trade-offs in High Performance Environments, VDM Verlag Dr. Muller, Germany: 9-11, 2010.
[17] G. Wang, J. Hao, J. Ma and L. Huang. A new approach to intrusion detection using Artificial Neural Networks and fuzzy clustering, 37(9): 6225-6232, 2010.
[18] L. Cherkasova, K. Ozonat, N. Mi, J. Symons and E. Smirni. Automated Anomaly Detection and Performance Modelling of Enterprise Applications. Journal of ACM Transactions on Computer Systems, 27(3): 6.1-6.32, 2009.
[19] DARPA Intrusion Detection Data sets. Cyber Systems and Technology. MIT Lincoln Laboratory,
[20] M. Tavallaee, E. Baghari, W. Lu and A. A. Ghorbani. A detailed analysis of the KDD CUP 99 datasets, In. Proc. 2nd IEEE Symposium on Computational Intelligence in Security and Defence Applications.53-58, 2009.
[21] J. C. Bezdek and L. I. Kuncheva. Nearest prototype classifier designs: An experimental study. International Journal of Intelligent Systems, 16(12): 1445-1473, 2001.
[22] D. S. Broomhead and D. Lowe. Radial basis functions, multi-variable functional interpolation and adaptive networks (Royal Signals and Radar Establishment Memorandum 4148). Royal Signals and Radar Establishment Malvern (United Kingdom).1-40, 1988.
[23] V. M. Rivas, J. J. Merelo, P. A. Castillo, M. G. Arenas and J. G. Castellano. Evolving RBF neural networks for time-series forecasting with EvRBF. Information Sciences, 165(3): 207-220, 2004.
[24] R. Rojas and J. Feldman. Neural Networks: A Systematic Introduction . Springer-Verlag, Berlin, New-York, 1996.
[25] I. G. Smotroff, D. H. Friedmanand D. Connolly. Self organizing modular neural networks, 1991. Available 155336/.
[26] H. B. Mann and D. R. Whitney On a test of whether one of two random variables is stochastically larger than the other. The Annals of Mathematical Statistics, 50-60, 1947.
[27] J. McHugh. Testing Intrusion Detection Systems: A Critique of the 1998 and 1999 DARPA Intrusion Detection System Evaluations as Performed by Lincoln Laboratory. ACM Transactions on Information and System Security. 3(4):2000. Available mchugh00.pdf.
[28] R. Caruana and A. Niculescu-Mizil. Data mining in metric space: an empirical analysis of supervised learning performance criteria. Proc.of the10th ACM SIGKDD int. conf. on Knowledge discovery and data mining, 2004.
[29] A. S. Aneetha and S. Bose. The combined approach for anomaly detection using neural networks and clustering techniques, Computer Science & Engineering. 2(4): 37- 46, 2012.
[30] M. Myers. Managing and Trobleshooting Networks, 2nd Ed., New Delhi, McGraw Hill, 2009.
[31] Neeraj Kumar, Upendra Kumar and G. Sahoo. Intrusion Detection Algorithm for data security. International Journal of Computer Trends and Technology (IJCTT) , 29 (3):158, 2015.

Neural Network, NSL-KDD, Intrusion Detection, Accuracy, LVQ, RBFN, DECR_RBFN, EVRBFN, MLP_BP, SONN.