An exemplar‐based learning approach for detection and classification of malicious network streams in honeynets. Issue 2 (29th May 2013)

• Record Type: Journal Article
• Authors: Abbasi, Fahim H.; Harris, Richard; Marsland, Stephen; Moretti, Giovanni
• Is Part Of: Security and communication networks. Volume 7:Issue 2(2014:Feb.)
• Page Start: 352
• Page End: 364
• Publication Date: 2013-05-29
• Subjects: Computer networks -- Security measures -- Periodicals; Computer security -- Periodicals; Cryptography -- Periodicals; 005.805
• DOI: 10.1002/sec.724
• Languages: English
• ISSNs: 1939-0114

Abstract

<abstract abstract-type="main"> <title>ABSTRACT</title> <p>Variants of malware and exploits are emerging globally at an ever‐increasing rate. There is a need to automate their detection by observing their footprints over network streams, but signature‐based intrusion detection systems alone cannot cope with the dynamic nature of modern security threats. In this paper, we approach intrusion detection as a classification problem and describe a system using exemplar‐based learning to correctly classify known classes of malware and to detect, learn and classify unknown malicious streams into classes. Copyright © 2013 John Wiley &amp; Sons, Ltd.</p> </abstract>