Improving Intrusion Detection with Adaptive Support Vector Machines

• Published in: Elektronika ir elektrotechnika Vol. 20; no. 7; p. 57
• Main Authors: Macek, N., Dordevic, B., Timcenko, V., Bojovic, M., Milosavljevic, M.
• Format: Journal Article
• Language: English
• Published: Kaunas University of Technology, Faculty of Telecommunications and Electronics 01.01.2014
• Subjects: Data security; Machine learning; Methods; Network architecture; Safety and security measures
• ISSN: 1392-1215; 2029-5731
• DOI: 10.5755/j01.eee.20.7.8025

The research topic that this paper is focused on is intrusion detection in critical network infrastructures, where discrimination of normal activity can be easily corrected, but no intrusions should remain undetected. The intrusion detection system presented in this paper is based on support vector machines that classify unknown data instances according both to the feature values and weight factors that represent importance of features towards the classification. The major contribution of the proposed model is significantly decreased false negative rate, even for the minor categories that have a very few instances in the training set, indicating that the proposed model is suitable for aforementioned environments. Index Terms--Intrusion detection, machine learning, support vector machines, false negative rate.