Computer Security As A Critical Problem For Computer Systems

3418 Words14 Pages
ABSTRACT Over the past decade computer networks have rapid growth, but the computer security became a critical problem for computer systems. Thus in the recent years various soft computing technique based methods were proposed to detects the growth of intrusion. Also many researchers have reported that the large set of pattern classifications and machine learning algorithms are trained and testing is made on the knowledge discovery data intrusion detection dataset is unsuccessful in finding the remote-to-local attacks and user-to root attacks. Moreover Hyperbolic Hopfield Neural Network(HHNN) based Intrusion Detection Systems (IDSs) detection stability, detection ratio, particularly low-frequent attacks are still required to be improved. Thus this paper proposes a new method known as K-Medoids-HNNN using the technique HHNN and K-Medoids clustering. This system achieves the higher intrusion detection rate, detection stability and less false positive rate. At first the proposed system implements the K-Medoids clustering technique on the various training subsets. Afterwards a mono HHNN model is trained using the different training subsets to detect the intrusion. The experimental results shows the K-Medoids-HHNN approach achieve better results rather than other framework.

Keywords: Network Security, Intrusion Detection System, Hyperbolic Hopfield Neural Network, K-Medoids Clustering approach

1. INTRODUCTION In the last decades, the computer network systems are very
Get Access