Pragmatic Analysis of Machine Learning Techniques in Network Based IDS

In providing defense to computer networks the network intrusion detection system (NIDS) plays a very essential role. To cope up with the demands of contemporary networks various concerns like performance evaluation and others related to the networks should be taken under consideration. Proposed work presents a pragmatic analysis of machine learning techniques for network based IDS. The performance analysis over two benchmark datasets i.e. KDD-Cup’99 and NSL-KDD by using five supervised machine learning techniques (RFC, Naive bayes, J48, Bayes Net and SVM) has been prepared. To assess the performance network based intrusion detection system various metrics such as accuracy, recall, F1-score and precision has been computed and analyzed. Therefore, the summary of the work suggests that no single technique is smart enough to identify all attack classes to conventional levels. Most of the techniques provided poor results for minority attack class(es). To estimate and assess the supervised classifier a blind set of investigation with 10-fold cross validation has been performed. The results achieved are promising and provides a new direction to researchers of the intrusion detection domain.

[1]  Jie Gu,et al.  An effective intrusion detection framework based on SVM with feature augmentation , 2017, Knowl. Based Syst..

[2]  Alan H. Fielding,et al.  An introduction to machine learning methods , 1999 .

[3]  Hemanta Kumar Kalita,et al.  Analysis of Machine Learning Techniques Based Intrusion Detection Systems , 2016 .

[4]  S. Devaraju,et al.  Performance analysis of intrusion detection system using various neural network classifiers , 2011, 2011 International Conference on Recent Trends in Information Technology (ICRTIT).

[5]  Danijela D. Protić,et al.  Review of KDD Cup '99, NSL-KDD and Kyoto 2006+ datasets , 2018 .

[6]  Shailendra Sahu,et al.  Network intrusion detection system using J48 Decision Tree , 2015, 2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

[7]  Harish Kumar,et al.  An intrusion detection system using network traffic profiling and online sequential extreme learning machine , 2015, Expert Syst. Appl..

[8]  Robert C. Atkinson,et al.  Shallow and Deep Networks Intrusion Detection System: A Taxonomy and Survey , 2017, ArXiv.

[9]  André C. Drummond,et al.  A Survey of Random Forest Based Methods for Intrusion Detection Systems , 2018, ACM Comput. Surv..

[10]  Xiangjian He,et al.  Building an Intrusion Detection System Using a Filter-Based Feature Selection Algorithm , 2016, IEEE Transactions on Computers.

[11]  Ethem Alpaydin,et al.  Introduction to machine learning , 2004, Adaptive computation and machine learning.

[12]  Sanjay Kumar,et al.  Machine learning classification model for Network based Intrusion Detection System , 2016, 2016 11th International Conference for Internet Technology and Secured Transactions (ICITST).

[13]  Mahdi Zamani,et al.  Machine Learning Techniques for Intrusion Detection , 2013, ArXiv.

[14]  Gulshan Kumar,et al.  AI based supervised classifiers: an analysis for intrusion detection , 2011, ACAI '11.

[15]  Xue Wang,et al.  Comparison deep learning method to traditional methods using for network intrusion detection , 2016, 2016 8th IEEE International Conference on Communication Software and Networks (ICCSN).

[16]  Dimitris Kanellopoulos,et al.  Handling imbalanced datasets: A review , 2006 .

[17]  Iftikhar Ahmad,et al.  Date of publication xxxx 00, 0000, date of current version xxxx 00, 0000 , 2018 .

[18]  Stefan Axelsson,et al.  Intrusion Detection Systems: A Survey and Taxonomy , 2002 .

[19]  Yinhui Li,et al.  An efficient intrusion detection system based on support vector machines and gradually feature removal method , 2012, Expert Syst. Appl..

[20]  Ali A. Ghorbani,et al.  A detailed analysis of the KDD CUP 99 data set , 2009, 2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications.

[21]  Vern Paxson,et al.  Outside the Closed World: On Using Machine Learning for Network Intrusion Detection , 2010, 2010 IEEE Symposium on Security and Privacy.

[22]  M. Sugumaran,et al.  Machine Learning Techniques for Intrusion Detection: A Comparative Analysis , 2016, ICIA.

[23]  Yalin Baştanlar,et al.  Introduction to machine learning. , 2014, Methods in molecular biology.

[24]  Balachandra Muniyal,et al.  Performance Evaluation of Supervised Machine Learning Algorithms for Intrusion Detection , 2016 .

[25]  Gustavo E. A. P. A. Batista,et al.  Learning with Skewed Class Distributions , 2002 .