A Feature Selection Algorithm to Find Optimal Feature Subsets for Detecting DoS Attacks

作者: Seung-Ho Kang

DOI: 10.1109/ICITCS.2015.7292916

关键词:

摘要: The performance of network intrusion detection systems based on machine learning techniques largely depends the selected features. However, choosing optimal subset features from a given feature set requires extensive computing resources. To tackle this problem we propose an selection algorithm local search algorithm. In order to evaluate our proposed algorithm, comparisons with composed all 41 are carried out over NSL-KDD data using multi-layer perceptron.

参考文章(8)
Hai Thanh Nguyen, Slobodan Petrović, Katrin Franke, A comparison of feature-selection methods for intrusion detection mathematical methods models and architectures for network security systems. pp. 242- 255 ,(2010) , 10.1007/978-3-642-14706-7_19
Ehsan Saboori, Shafigh Parsazad, Amin Allahyar, Fast Feature Reduction in intrusion detection datasets international convention on information and communication technology, electronics and microelectronics. pp. 1023- 1029 ,(2012)
Zenglin Xu, Irwin King, Michael Rung-Tsong Lyu, Rong Jin, Discriminative Semi-Supervised Feature Selection Via Manifold Regularization IEEE Transactions on Neural Networks. ,vol. 21, pp. 1033- 1047 ,(2010) , 10.1109/TNN.2010.2047114
Chandrashekhar Azad, Vijay Kumar Jha, Data Mining in Intrusion Detection: A Comparative Study of Methods, Types and Data Sets International Journal of Information Technology and Computer Science. ,vol. 5, pp. 75- 90 ,(2013) , 10.5815/IJITCS.2013.08.08
Girish Chandrashekar, Ferat Sahin, A survey on feature selection methods Computers & Electrical Engineering. ,vol. 40, pp. 16- 28 ,(2014) , 10.1016/J.COMPELECENG.2013.11.024
H G Kayacik, A N Zincir Heywood, M I Heywood, SELECTING FEATURES FOR INTRUSION DETECTION: A FEATURE RELEVANCE ANALYSIS ON KDD 99 INTRUSION DETECTION DATASETS PROCEEDINGS OF THE ANNUAL CONFERENCE ON PRIVACY, SECURITY AND TRUST. pp. 0- 0 ,(2005)
Adetunmbi A Olusola, Adeola S Oladele, Daramola O Abosede, None, Analysis of KDD '99 Intrusion Detection Dataset for Selection of Relevance Features ,(2010)