文章基本信息

标题：MACHINE LEARNING TECHNIQUES FOR INTRUSION DETECTION SYSTEM: A REVIEW
本地全文：下载
作者：SUNDUS JUMA ; ZAITON MUDA ; M.A. MOHAMED 等
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2015
卷号：72
期号：3
出版社：Journal of Theoretical and Applied
摘要：Intrusion detection is considered as one of the foremost research areas in network security, the challenge is to recognize unusual access that could lead to compromising the interconnected nodes. Anomaly-based intrusion detection system, that utilizes machine learning techniques such as single classifier and hybrid classifier have the capability to recognize unpredicted malevolent. In this paper, we examine different machine learning techniques that have been proposed for detecting intrusion by focusing on the hybrid classifier algorithms. The objective is to determine their strengths and weaknesses. From the comparison, we hope to identify the gap for developing an efficient intrusion detection system that is yet to be researched.
关键词：Intrusion Detection; Anomaly Detection; Machine Learning; Hybrid Classifier; Single Classifier