Enhancing Intrusion Detection Systems Using Intelligent False Alarm Filter: Selecting the Best Machine Learning Algorithm

View Sample PDF

Author(s): Yuxin Meng (City University of Hong Kong, China)and Lam-For Kwok (City University of Hong Kong, China)
Copyright: 2014
Pages: 23
Source title: Architectures and Protocols for Secure Information Technology Infrastructures
Source Author(s)/Editor(s): Antonio Ruiz-Martinez (University of Murcia, Spain), Rafael Marin-Lopez (University of Murcia, Spain)and Fernando Pereniguez-Garcia (University of Murcia, Spain)
DOI: 10.4018/978-1-4666-4514-1.ch008

Keywords: Information Science Reference / Information Security & Privacy / IT Security and Ethics / Security & Forensics

Purchase

View Enhancing Intrusion Detection Systems Using Intelligent False Alarm Filter: Selecting the Best Machine Learning Algorithm on the publisher's website for pricing and purchasing information.

Abstract

Intrusion Detection Systems (IDSs) have been widely implemented in various network environments as an essential component for current Information and Communications Technologies (ICT). However, false alarms are a big problem for these systems, in which a large number of IDS alarms, especially false positives, could be generated during their detection. This issue greatly decreases the effectiveness and the efficiency of an IDS and heavily increases the burden on analyzing real alarms. To mitigate this problem, in this chapter, the authors identify and analyze the reasons for causing this problem, present a survey through reviewing some related work in the aspect of false alarm reduction, and introduce a promising solution of constructing an intelligent false alarm filter to refine false alarms for an IDS.

The IRMA Community

Research IRM

Enhancing Intrusion Detection Systems Using Intelligent False Alarm Filter: Selecting the Best Machine Learning Algorithm

Purchase

Abstract

Related Content

IRMA Sponsors