Improving Intrusion Detection using Genetic Linear Discriminant Analysis

Authors

  • Azween Bin Abdullah Taylors University
  • Long Zheng Cai Unitar International University

Keywords:

IDS, Features selection, Features transformation, NSL-KDD, GLDA, SVM Kernels

Abstract

The objective of this research is to propose an efficient soft computing approach with high detection rates and low false alarms while maintaining low cost and shorter detection time for intrusion detection. Our results were promising as they showed the new proposed system, hybrid feature selection approach of Linear Discriminant Analysis and Genetic Algorithm (GA) called Genetic Linear Discriminant Analysis (GLDA) and Support Vector Machines (SVM) Kernels as classifiers with different combinations of NSL-KDD data sets is an improved and effective solution for intrusion detection system (IDS).

Downloads

Download data is not yet available.

Author Biographies

Azween Bin Abdullah, Taylors University

Azween Abdullah has been contributing to research, teaching, consulting and in administrative services to the institutions that he has been working for thus far. His work experience includes twenty five years as a academic in institutions of higher learning and as director of research and academic affairs at two institutions of higher learning, vice-president for educational consultancy services, ten years in commercial companies as Software Engineer, Systems Analyst and as a computer software developer and IT/MIS consultancy and training. He is currently a senior academic at Taylors University and holds the position of Vice-President (Academic and IT) at CyEduLab Sdn. Bhd. and as CTO in Prospere Solutions Sdn. Bhd. As well as the Adjunct Research professor He has guided twelve PhD students and ten Masters students under his supervision.   He is responsible for the full-range of consulting services for the academic and IT related industries. He is a fellow of the British Computer Society and members of IEEE and ACM. His area of specialization  is in Bio-Inspired Computation and Computer and Wireless Security. He has been consulting for some technology companies in content development and has done research on emerging areas of networked and quantum security. Azween Abdullah has extensive consultancy experience both locally and abroad for development projects on enterprise and sales systems, as well as system integration projects. He has been involved with a number of government and semi-government organisations in Malaysia in the role of External Consultant. He has also published more than 150 publications in various technical journals and conference proceedings and has given technical talks in a number of key international conferences, industry summits and forums. Azween is an eminent scholar and an able administrator at par excellence. He has worked as member of various expert committees of UGC for evaluation of the proposals to organize seminars/conferences/workshop, to sanction and evaluation of major projects and to provide financial support to special assistance program.

 

Long Zheng Cai, Unitar International University

Cai Long Zheng is currently an assistant professor at faculty of business and IT, Unitar International University. His area of research is in computer security.

References

A. Martinez and A. Kak (2001). "PCA versus LDA", IEEE Transactions on Pattern Analysis and Machine Intelligence,” vol. 23, no. 2, pp. 228-233,.

China Papers Online (2011). “Study on Application of Hybrid Soft-Computing Technique to Intrusion Detection”.

Adel Nadjaran Toosi and Mohsen Kahani (2007) “A new approach to intrusion detection based on an evolutionary soft computing model using neuro-fuzzy classifiers,” Department of Computer, Ferdowsi University of Mashhad, Iran.

Kresimir Delac, Mislav Grgic and Sonja Grgic (2006). “Independent Comparative Study of PCA, ICA, and LDA on the FERET Data Set,” University of Zagreb, FER, Unska 3/XII, Croatia.

J. McHugh (2000) “Testing intrusion detection systems: a critique of the 1998 and 1999 DARPA intrusion detection,” ACM Transactions on Information and System Security.

Shailendra Singh, Sanjay Silakari and Ravindra Patel (2011). An Efficient Feature Reduction Technique for Intrusion Detection System, IPCSIT, Vol. 3.

Ahmad I, Abdullah AB, and Alghamdi (2011). “Intrusion detection using feature subset selction based on MLP,” Scientific Research and Essays, Vol 6(34).

S. M. Aqil, M. Sadiq Ali Khan and Jawed Naeem (2010). Efficient Probabilistic Classification Methods for NIDS, IJCSIS, Vol. 8, No. 8, November.

P. Belhumeur, J. Hespanha, and D. Kriegman (1996). Eigenfaces vs. fisherfaces: Recognition using class specific linear projection, Proc Fourth Eur Conf Computer Vision, Vol. 1, 1418, pp. 45–58.

M. Turk and A. Pentland (1991). “Eigenfaces for recognition,” J Cogn Neurosci 3, 71–86.

K. Baek, B. Draper, J.R. Beveridge and K. She (2002). "PCA vs. ICA: A Comparison on the FERET Data Set,” Proc. of the Fourth International Conference on Computer Vision, Pattern Recognition and Image Processing, Durham, NC, USA, 8-14, pp. 824-827.

Chittur A. (2006). “Model Generation for an Intrusion Detection System Using Genetic Algorithms,” High school Honors Thesis.

Acohido B. (2009). "Hackers breach heartland payment credit card system", 11 March.

Abraham A. and Jain R. (2008). "Soft computing models for network intrusion detection systems, 15 May.

Sandhya P., Ajith A., Crina G. and Thomas J. (2005). "Modeling intrusion detection system using hybrid intelligent systems. Journal of Network and Computer Applications,".

Ilgun K, Kemmerer R.A. and Porras P.A. (1995). "State transition analysis: a rule-based intrusion detection approach," IEEE Trans Software Eng 21(3):181–199.

Zadeh LA. (1994). "History; bisc during 90’s,".

Zadeh L.A. (1998). "Roles of soft computing and fuzzy logic in the conception," design and deployment of information/intelligent systems. In: Kaynak O, Zadeh LA, Turksen B, Rudas IJ (eds) Computational intelligence: soft computing and fuzzy-neuro integration with applications, vol 162. Springer, New York.

Rupali D. (2010). "Feature Reduction for Intrusion Detection Using Linear Discriminant Analysis", (IJCSE) International Journal on Computer Science and Engineering Vol. 02, No. 04, 1072-1078.

Liao Y. and Vemuri V. R. (2002). "Use of k-nearest neighbor classifier for intrusion detection," Computer Security, vol. 21, no. 5, pp. 439-448.

Selvakani Kandeeban S. and Rengan S. R. (2010). "Integrated Intrusion Detection System Using Soft Computing", I. J. Network Security 10(2): 87-92. 2008.

M.Sadiq Ali Khan (2012). "Application of Statistical Process Control Methods for IDS," International Journal of Computer Science Issues, Vol. 9, Issue 6, No 1, November.

Chittur A. (2006). “Model Generation for an Intrusion Detection System Using Genetic Algorithms,” High school Honors Thesis, accessed in.

Downloads

Published

03.03.2015

How to Cite

Abdullah, A. B., & Cai, L. Z. (2015). Improving Intrusion Detection using Genetic Linear Discriminant Analysis. International Journal of Intelligent Systems and Applications in Engineering, 3(1), 34–39. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/119

Issue

Vol. 3 No. 1 (2015)

Section

Research Article

License

All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.

IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.