Abstract
Intrusion Detection system is an active and driving secure technology. Intrusion detection (ID) is the process of examining the events occurring in a computer system or network. Analyzing the system or network for signs of intrusions, defined as attempts to compromise the confidentiality, integrity, availability, or to bypass the security mechanisms of a network. The focus of this paper is mainly on intrusion detection based on data mining. The main part of Intrusion Detection Systems (IDSs) is to produce huge volumes of alarms. The interesting alarms are always mixed with unwanted, non-interesting and duplicate alarms. The aim of data mining is to improve the detection rate and decrease the false alarm rate. So, here we proposed a framework which detect the intrusion and after that, it will show the improvement of k-means clustering algorithm.