A Novel Algorithm to Minimize False Alarm in Network Intrusion Detection System

Abstract

Network intrusion detection systems (NIDS) are widely deployed in various network environments. Compared to an anomaly based NIDS, a signature-based NIDS is more popular in real-world applications, because of its relatively lower false alarm rate. In today’s era the security of computer system is of great concern. Because the last few years have seen a dramatic increase in the number of attacks, intrusion detection has become the mainstream of information assurance. While firewalls do provide some protection, they do not provide full protection and still need to be complimented by an intrusion detection system (IDS). Data mining techniques are a new approach for Intrusion detection. IDS system can be developed using individual algorithms like classification, neural networks, clustering etc. Such system yields good detection rate and less false alarm rate. Recent studies show that as compared to the single algorithm, cascading of multiple algorithms gives much better performance. False alarm rate was also high in such system. Therefore combination of different algorithms is performed to solve this problem. This paper we uses three hybrid algorithms for developing the intrusion detection system to minimize false alarm rate such as Possible Attack Signature, Known Attack Detection and Possible Attack Detection.