Empirical Performance Evaluation Of Feature Selection Approach For Network Intrusion Detection

Internet use has dramatically increased in the last decade with the advent of efficient and affordable technology. The organizations and the companies are using the Internet to boost up their efficiency and for effective communication but there is always a threat of security breaches that can be disastrous for them. The number of security attacks has been exponentially increased in the last decade and there is a need for efficient intrusion detection systems. The classical rule-based or behavior-based intrusion detection system can identify known attacks but they very inefficient in detecting unknown attacks. Researchers are applying machine learning techniques to detect unknown attacks by using various clustering and classification techniques. In this paper, we have evaluated the performance of feature selection (filter and wrapper method) with Naïve Bayes, OneR, Adaboost, J48 decision tree for detection the attacks. We have used UNSW_NB15 data set and performance evaluations are performed on the basis of Precision, accuracy, recall, MCC and sensitivity. The outcomes of experiments show that the feature selection methods enhance the performance of Bayes, OneR, Adaboost, J48.

REFERENCES

[1] Kaushik, Sapna S., and P. R. Deshmukh. "Detection of attacks in an intrusion detection system." International Journal of Computer Science and Information Technologies (IJCSIT) 2, no. 3 (2011): 982-986.
[2] Alkasassbeh, Mouhammd. "An empirical evaluation for the intrusion detection features based on machine learning and feature selection methods." arXiv preprint arXiv:1712.09623(2017).
[3] Horng, Shi-Jinn, Ming-Yang Su, Yuan-Hsin Chen, Tzong-Wann Kao, Rong-Jian Chen, Jui-Lin Lai, and Citra Dwi Perkasa. "A novel intrusion detection system based on hierarchical clustering and support vector machines." Expert systems with Applications 38, no. 1 (2011): 306-313.
[4] Yitzhaky, Yitzhak, and Eli Peli. "A method for objective edge detection evaluation and detector parameter selection." IEEE Transactions on pattern analysis and machine intelligence 25, no. 8 (2003): 1027-1033.
[5] Moustafa, Nour, and Jill Slay. "UNSW-NB15: a comprehensive data set for network intrusion detection systems (UNSW-NB15 network data set)." In 2015 military communications and information systems conference (MilCIS), pp. 1-6. IEEE, 2015.
[1] Kaushik, Sapna S., and P. R. Deshmukh. "Detection of attacks in an intrusion detection system." International Journal of Computer Science and Information Technologies (IJCSIT) 2, no. 3 (2011): 982-986.
[2] Alkasassbeh, Mouhammd. "An empirical evaluation for the intrusion detection features based on machine learning and feature selection methods." arXiv preprint arXiv:1712.09623(2017).
[3] Horng, Shi-Jinn, Ming-Yang Su, Yuan-Hsin Chen, Tzong-Wann Kao, Rong-Jian Chen, Jui-Lin Lai, and Citra Dwi Perkasa. "A novel intrusion detection system based on hierarchical clustering and support vector machines." Expert systems with Applications 38, no. 1 (2011): 306-313.
[4] Yitzhaky, Yitzhak, and Eli Peli. "A method for objective edge detection evaluation and detector parameter selection." IEEE Transactions on pattern analysis and machine intelligence 25, no. 8 (2003): 1027-1033.
[5] Moustafa, Nour, and Jill Slay. "UNSW-NB15: a comprehensive data set for network intrusion detection systems (UNSW-NB15 network data set)." In 2015 military communications and information systems conference (MilCIS), pp. 1-6. IEEE, 2015.

[7] Chen, Jingnian, Houkuan Huang, Shengfeng Tian, and Youli Qu. "Feature selection for text classification with Naïve Bayes." Expert Systems with
[8] Applications 36, no. 3 (2009): 5432-5435.
[9] Soman, Thara, and Patrick O. Bobbie. "Classification of arrhythmia using machine learning techniques." WSEAS Transactions on computers 4, no. 6 (2005): 548-552.
[10] Schapire, Robert E. "The boosting approach to machine learning: An overview." In Nonlinear estimation and classification, pp. 149-171. Springer, New York, NY, 2003.
[11] Firdausi, Ivan, Alva Erwin, and Anto Satriyo Nugroho. "Analysis of machine learning techniques used in behavior-based malware detection." In 2010 second international conference on advances in computing, control, and telecommunication technologies, pp. 201-203. IEEE, 2010.