Feature selection for intrusion detection systems
Firuz Kamalov, Sherif Moussa, Rita Zgheib, Omar Mashaal
Abstract
In this paper, we analyze existing feature selection methods to identify the key elements of network traffic data that allow intrusion detection. In addition, we propose a new feature selection method that addresses the challenge of considering continuous input features and discrete target values. We show that the proposed method performs well against the benchmark selection methods. We use our findings to develop a highly effective machine learning-based detection systems that achieves 99.9% accuracy in distinguishing between DDoS and benign signals. We believe that our results can be useful to experts who are interested in designing and building automated intrusion detection systems.
Topics & Concepts
Intrusion detection systemComputer scienceFeature selectionBenchmark (surveying)Artificial intelligenceSelection (genetic algorithm)Data miningKey (lock)Machine learningDenial-of-service attackFeature (linguistics)Feature extractionThe InternetComputer securityLinguisticsGeodesyPhilosophyGeographyWorld Wide WebNetwork Security and Intrusion DetectionAnomaly Detection Techniques and ApplicationsInternet Traffic Analysis and Secure E-voting