作者: Rania A. Ghazy , El-Sayed M. EL-Rabaie , Moawad I. Dessouky , Nawal A. El-Fishawy , Fathi E. Abd El-Samie
DOI: 10.1007/S11277-018-5662-0
关键词: Data mining 、 Computer science 、 Intrusion detection system 、 Denial-of-service attack 、 Classifier (UML) 、 Feature selection
摘要: With the growth and benefits of network usage, securing networks by using anomaly intrusion detection systems (IDS) against unknown intrusions has become an important issue. The first step protecting any is attacks. In this paper, we concentrate on four attacks; denial service (DoS), probing, remote-to-local, user-to-root We depend features extracted from (NSL-KDD) dataset for these investigate performance attack process several numbers various subset-based feature selection techniques aiming to find optimum collection detecting each with appropriate classifier. Simulation results reveal that redundant can be eliminated process, determine most useful set a certain classifier, which enhances IDS performance.