To Decrease the Issue of False Alarm Rate by Providing Authentication & Thus Improving the Efficiency of Intrusion Detection System by Comparing the Result of Filtered Clusterer Algorithm Make-Density Based Clustering Algorithm without Attribute Count

Abstract

The Intrusion Detection System sends alerts when it detects doubtful activities while monitoring the network traffic and other known threats. In today’s time in the field of Cyber security Intrusion Detection is considered a brilliant topic that could be objective. But it might not remain objectionable for a longer period. For understanding Intrusion Detection, the meaning of Intrusion must be clear at first. According to the oxford’s learners dictionary “Intrusion is the act of entering a place that is private or where you may not be wanted”. For this article, here it defines intrusion as any un-possessed system or network festivity on one (or more) computer(s) or network(s). Here is the example of a faithful user trying to access the system taking more than the usual trial counts to complete his access to the particular account or trying to connect to an unauthorized remote port of a server. The ex-employee who was being fired lately can provoke intrusion or any authentic worker can also provoke intrusion or any other person from the outside world could perform it. In this clause, the average data is found as the attack which is considered as the case of false positive. In this paper, the main focus is on the illustration and a solution offered for the same problem. Here we are using the KDD CUP 1999 data set. According to the outcome, the anomaly class is the one that has a higher number of counts than this class. Even if it is the true user trying to get access but the outcome is an anomaly due to the high number of counts in the class. This paper introduces a solution for the detection of a true person and eradicates the false positive.