基于机器学习的入侵检测研究  

Research on intrusion detection system based on machine learning

作　　者：刘明川[1] 彭长生[1] 

机构地区：[1]重庆邮电大学成人教育学院,重庆400065

出　　处：《计算机工程与设计》2008年第11期2736-2738,2741,共4页Computer Engineering and Design

摘　　要：针对现有的检测技术和入侵检测系统还存在一些问题和不足,提出将机器学习方法应用在入侵检测系统中,建立了一个基于学习的入侵检测系统模型,给出了一个基于机器学习的入侵检测系统的设计。该系统不仅能通过模式匹配的方式检测到一些已知的攻击,还能通过自我学习检测到未知的攻击。There are some problems in current intrusion detection technique. Aimed at these issues, a general intrusion detection system based on machine learning is proposed and the system model architecture diagram, the main flow steps of the system model are given; and then the machine learning module is designed and tested. This module mainly applies LERAD algorithm that belongs to machine learning. LERAD is from Matthew Vincent Mahoney＇s doctor paper in first reference literature list. The system can not only detect the known attacks by pattern matching, but also detect the unknown attacks by self learning.

关 键 词：网络安全 入侵检测 入侵检测系统 机器学习 数据包嗅探器 误用检测 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]