Nonlinear Feature Transformation and Genetic Feature Selection: Improving System Security and Decreasing Computational Cost

ETRI Journal

关键词: genetic algorithm;    feature selection;    feature transformation;    Intrusion detection system;   

Others  :  1186180
DOI  :  10.4218/etrij.12.1812.0032

【 摘 要 】

Intrusion detection systems (IDSs) have an important effect on system defense and security. Recently, most IDS methods have used transformed features, selected features, or original features. Both feature transformation and feature selection have their advantages. Neighborhood component analysis feature transformation and genetic feature selection (NCAGAFS) is proposed in this research. NCAGAFS is based on soft computing and data mining and uses the advantages of both transformation and selection. This method transforms features via neighborhood component analysis and chooses the best features with a classifier based on a genetic feature selection method. This novel approach is verified using the KDD Cup99 dataset, demonstrating higher performances than other well-known methods under various classifiers have demonstrated.

   

【 参考文献 】

• [1]T. Bhaskar et al., "A Hybrid Model for Network Security Systems: Integrating Intrusion Detection System with Survivability," Int. J. Netw. Security, vol. 7, no. 2, 2008, pp. 249-260.
• [2]P. Kabiri and A. Ghorbani, "Research on Intrusion Detection and Response: A Survey," Int. J. Netw. Security, vol. 1, no. 2, 2005, pp. 84-102.
• [3]I.-V. Onut A. Ghorbani, "A Feature Classification Scheme for Network Intrusion Detection," Int. J. Netw. Security, vol. 5, no. 1, 2007, pp. 1-15.
• [4]Z. Zhang et al., "An Observation-Centric Analysis on the Modeling of Anomaly-based Intrusion Detection," Int. J. Netw. Security, vol. 4, no. 3, 2007, pp. 292-305.
• [5]S.S. Kandeeban and R. Rajesh, "Integrated Intrusion Detection System Using Soft Computing," Int. J. Netw. Security, vol. 10, no. 2, Mar. 2010, pp. 87-92.
• [6]N. Srinivasan and V. Vaidehi, "Performance Analysis of Soft Computing Based Anomaly Detectors," Int. J. Netw. Security, vol. 7, no. 3, 2008, pp. 436-447.
• [7]P. Langley, Elements of Machine Learning, San Francisco, CA: Morgan Kaufmann, 1996.
• [8]K. Fukunaga, Introduction to Statistical Pattern Recognition, Boston, MA: Academic Press, 1990.
• [9]L.O. Jimenez and D. Landgrebe, "Supervised Classification in High-Dimensional Space: Geometrical, Statistical and Asymptotical Properties of Multivariate Data," IEEE Trans. Syst., Man, Cybern., vol. 28, no. 1, 1997, pp. 39-54.
• [10]K. Pearson, "On Lines and Planes of Closest Fit to Systems of Points in Space," Philosophical Mag., vol. 2, no. 11, 1901, pp. 559-572.
• [11]C. Spearman, "General Intelligence Objectively Determined and Measured," American J. Psychology, vol. 15, no. 2, 1904, pp. 206-221.
• [12]S. Axler, Linear Algebra Done Right, New York, NY: Springer-Verlag, 1995.
• [13]W.S. Torgerson, "Multidimensional Scaling I: Theory and Method," Psychometrika, vol. 17, 1952, pp. 401-419.
• [14]M.J. Middlemiss and G. Dick, "Weighted Feature Extraction Using a Genetic Algorithm for Intrusion Detection," Evolutionary Computation, vol. 3, 2003, pp. 1699-1675.
• [15]T. Xia et al., "An Efficient Network Intrusion Detection Method Based on Information Theory and Genetic Algorithm," Proc. 24th IEEE Int. Performance Comput. Commun. Conf., Apr. 2005, pp. 11-17.
• [16]A. Chittur; Model Generation for an Intrusion Detection System Using Genetic Algorithms, high school honors thesis, Ossining High School, Ossining, NY, USA, Nov. 2001.
• [17]W. Lu and I. Traore, "Detecting New Forms of Network Intrusion Using Genetic Programming," Computational Intell., Malden, MA: Blackwell Publishing, vol. 20, no. 3, 2004, pp. 475-494.
• [18]W. Li, "Using Genetic Algorithm for Network Intrusion Detection," SANS Institute, USA, 2004.
• [19]G. Jian, L. Da-xin, and C. Bin-ge, "An Induction Learning Approach for Building Intrusion Detection Models Using Genetic Algorithms," Proc. 5th World Congress Intell. Control Autom., June 15-19, vol. 5, 2004, pp. 4339-4342.
• [20]J. Goldberger et al., "Neighborhood Components Analysis," Proc. Adv. Neural Inf. Process., Whistler, BC, Canada, 2005, pp. 571-577.
• [21]N. Singh-Miller, M. Collins, and T.J. Hazen, "Dimensionality Reduction for Speech Recognition Using Neighborhood Components Analysis," Proc. Interspeech, 2007, pp. 1158-1161.
• [22]A. Amine et al., "GA-SVM and Mutual Information Based Frequency Feature Selection for Face Recognition" GSCM-LRIT, Faculty of Sciences, Mohammed V University, B.P. 1014, Rabat, Morocco.
• [23]S. Sethuramalingam and E.R. Naganathan, "Hybrid Feature Selection for Network Intrusion," Int. J. Computer Sci. Eng., vol. 3, no. 5, 2011, pp. 1773-1780.
• [24]http://kdd.ics.uci.edu/databases/kddcup99/kddcup99.htm
• [25]S. Axelsson, "The Base-Rate Fallacy and the Difficulty of Intrusion Detection," ACM Trans. Inf. Syst. Security, vol. 3, no. 3, Aug. 2000, pp. 186-205.
• [26]P. Dokas et al., "Data Mining for Network Intrusion Detection," Proc. NSF Workshop Next Generation Data Mining (NGDM), 2002, pp. 21-30.
• [27]T. Fawcett, "An Introduction to ROC Analysis," Pattern Recog. Lett., vol. 27, no. 8, 2006, pp. 861-874.
• [28]G. Liu and Z. Yi, "Intrusion Detection Using PCASOM Neural Networks," Advances in Neural Networks – ISNN 2006, J. Wang et al., Eds., Berlin/Heidelberg: Springer-Verlag, 2006, pp. 240-245.
• [29]I. Ahmad et al., "Optimized Intrusion Detection Mechanism Using Soft Computing Techniques," Telecommun. Syst., 2011, doi: 10.1007/s11235-011-9541-1.
• [30]H. Abbasian et al., "Class Dependent LDA Optimization Using Genetic Algorithm for Robust MFCC Extraction," Adv. Computer Sci. Eng., vol. 6, 2009, pp. 807-810.
• [31]J.C. Dunn, "Well-Separated Clusters and Optimal Fuzzy Partitions," J. Cybern., vol. 4, no. 1, 1974, pp. 95-104.
• [32]M. Halkidi, M. Vazirgiannis, and Y. Batistakis, "Quality Scheme Assessment in the Clustering Process," Proc. 4th European Conf. Principles Data Mining Knowledge Discovery, LNCS, vol. 1910, 2000, pp. 265-276.