Anzeige
Erschienen in:
05.05.2018
Efficient Techniques for Attack Detection Using Different Features Selection Algorithms and Classifiers
Erschienen in: Wireless Personal Communications | Ausgabe 4/2018
EinloggenAktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
With the growth and benefits of network usage, securing the networks by using anomaly intrusion detection systems (IDS) against unknown intrusions has become an important issue. The first step of protecting any network is the detection of attacks. In this paper, we concentrate on four attacks; denial of service (DoS), probing, remote-to-local, and user-to-root attacks. We depend on features extracted from (NSL-KDD) dataset for these attacks. We investigate the performance of the attack detection process for several numbers of features using various subset-based feature selection techniques aiming to find the optimum collection of features for detecting each attack with an appropriate classifier. Simulation results reveal that redundant features can be eliminated from the attack detection process, and that we can determine the most useful set of features for a certain classifier, which enhances the IDS performance.