期刊名称：International Journal of Computer Science & Technology
印刷版ISSN：2229-4333
电子版ISSN：0976-8491
出版年度：2013
卷号：4
期号：2
页码：84-87
语种：English
出版社：Ayushmaan Technologies
摘要：Due to world wide connectivity through Internet, the complexity of network attacks, as well as their sternness, has also increased recently. As such, more and more organizations are becoming vulnerable to attack. An intrusion detection system’s main goal is to classify activities of a system into two major categories: normal and suspicious (intrusive) activities. Intrusion detection systems usually specify the type of attack or classify activities in some specific groups The aim of this research paper is to classify network attacks using soft computing approach here we used two class classifier SVM(Support Vector Machine) which leads to a higher detection rate and a lower false alarm rate in a shorter time. This paper focuses on the classes, Normal, DoS (Smurf, Back), Probing (Ipsweep). Extensive analysis is conducted in order to assess the translation of symbolic data, partitioning of the training data. The experiments and evaluations of the proposed method were performed with the KDD Cup 99 intrusion detection dataset. Experimental result shows that system archive 25% improvement. If only 5% false prediction are used.
