期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2014
卷号：62
期号：1
出版社：Journal of Theoretical and Applied
摘要：Internet is a useful source of information in everyone�s daily activity. Internet becomes a globally used public network. Significance of Intrusion detection system (IDS) in computer network security is well proven. In order to protect the organization data, Intrusion Detection System (IDS) offers protection from external users and internal attackers. Intrusion detection is the processes of examining the events which happens in a computer system or network and evaluate them for signs of possible events, which are imminent threats of violation of computer security policies, standard security practices and acceptable use policies. In this paper a new algorithm is introduced to find out the protocol and their attacks are Fast Hierarchical Relevance Vector Machine (FHRVM). These algorithms are formed by the combination of RVM with LM-AHP. The main goal of the paper, that successful identification of attacks in reduced false alarm rate. To demonstrate this by exploiting a probabilistic Bayesian learning framework, in this paper derive an accurate prediction models which typically utilize dramatically fewer basis functions than a comparable KSVM and FHELM. These include the benefits of probabilistic predictions, automatic estimation of `nuisance' parameters and the facility to utilize arbitrary basis functions. The experiment is carried out with the help of MATLAB by using KDD Cup 1999 dataset and the results indicate that the proposed technique can achieve higher detection rate and very low false 7alarm rate than the regular KSVM, FHELM algorithms.
