Ca-NIDS: A network intrusion detection system using combinatorial algorithm approach
Olusegun Folorunso,
Femi Emmanuel Ayo and
Y. E. Babalola
Journal of Information Privacy and Security, 2016, vol. 12, issue 4, 181-196
Abstract:
A signature-based system (SBS) is a common approach for intrusion detection and the most preferable by researchers. In spite of the popularity of SBS, it cannot detect new attacks on the network compared to anomaly-based systems (ABS). The most challenging problem of SBS is keeping an up-to-date database of known attack signatures and the setting of a suitable threshold level for intrusion detection. In this article, a network intrusion detection system based on combinatorial algorithm (CA-NIDS) is proposed. The CA-NIDS uses additional databases to enable the SBS to act as an ABS for the purpose of detecting new attacks and to speed up network traffic during traffic analysis by the combinatorial algorithm. A suitable threshold of 12 was also set based on the study of past works to lower the false positive rate. The CA-NIDS was evaluated with similar online schemes and result shows a small false-positive rate of 3% and a better accuracy of 96.5% compared with related online algorithms.
Date: 2016
References: Add references at CitEc
Citations: View citations in EconPapers (1)
Downloads: (external link)
http://hdl.handle.net/10.1080/15536548.2016.1257680 (text/html)
Access to full text is restricted to subscribers.
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:taf:uipsxx:v:12:y:2016:i:4:p:181-196
Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/uips20
DOI: 10.1080/15536548.2016.1257680
Access Statistics for this article
Journal of Information Privacy and Security is currently edited by Chuleeporn Changchit
More articles in Journal of Information Privacy and Security from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().