Intrusion detection is a classification problem where the classification accuracy is very important. In network intrusion detection, the large number of features increases the time and space cost. As the irrelevant features make noisy data, feature selection plays essential role in intrusion detection. The process of selecting best feature is the vital role to ensure the performance, speed, accuracy and reliability of the detector. In this paper we propose a new feature selection method based on Genetic Algorithm in order to improve detection accuracy and efficiency. Here the Genetic Algorithm is used for the best feature selection and optimization. The Back Propagation Neural Network is used to evaluate the performance of the detector in terms of detection accuracy. To verify this approach, we used KDD Cup99 dataset. © 2011 Springer-Verlag.
CITATION STYLE
Gomathy, A., & Lakshmipathi, B. (2011). Network intrusion detection using genetic algorithm and neural network. In Communications in Computer and Information Science (Vol. 198 CCIS, pp. 399–408). https://doi.org/10.1007/978-3-642-22555-0_41
Mendeley helps you to discover research relevant for your work.