期刊名称：International Journal of Computer Science Issues
印刷版ISSN：1694-0784
电子版ISSN：1694-0814
出版年度：2013
卷号：10
期号：6
出版社：IJCSI Press
摘要：Intrusion detection system (IDS) is an important tool for the defense of a network against attacks. It monitors the activities occurring in a computer system or network and analyzes them for recognizing intrusions to protect the computer network. Most of the existing IDSs use all of the 41 features available in the network packet to analyze and look for intrusive pattern, while some of these features are redundant and irrelevant. The weakness of this approach is the time-consuming during detection process and degrading the performance of IDSs. A well-defined feature selection algorithm makes the classification process more effective and efficient. In this paper a new hybrid algorithm NNIV-RS (Neural Network with Indicator Variable using Rough Set for attribute reduction) algorithm is used to reduce the amount of computer resources like memory and CPU time required to detect attack. Rough Set Theory is used to select out feature reducts. Indicator Variable is used to represent dataset in more efficient way. Neural network is used for network traffic packet classification. Tests and comparison were done on NSL-KDD dataset which is the improved version of KDD99 data set. The experiments results showed that the proposed algorithm gives better and robust representation of data as it was able to select features resulting in 80.4% data reduction, select significant attributes from the selected features and achieve detection accuracy about 96.7% with a false alarm rate of 3%.
