Title :
Attack Characterization and Intrusion Detection using an Ensemble of Self-Organizing Maps
Author :
DeLooze, Lori L.
Abstract :
Self-organized maps (SOM) use an unsupervised learning technique to independently organize a set of input patterns into various classes. In this paper, we use an ensemble of SOMs to identify computer attacks and characterize them appropriately using the major classes of computer attacks (denial of service, probe, user-to-root and remote-to-local). The procedure produces a set of confidence levels for each connection as a way to describe the connection´s behavior
Keywords :
learning (artificial intelligence); security of data; self-organising feature maps; attack characterization; computer attacks; denial of service; intrusion detection; remote-to-local attacks; self-organizing maps; unsupervised learning technique; user-to-root attacks; Computer crime; Computerized monitoring; Data security; Intrusion detection; Neural networks; Probes; Remote monitoring; Self organizing feature maps; Telecommunication traffic; Unsupervised learning;
Conference_Titel :
Information Assurance Workshop, 2006 IEEE
Conference_Location :
West Point, NY
Print_ISBN :
1-4244-0130-5
DOI :
10.1109/IAW.2006.1652084
