摘要
信息安全是全球关注的重要话题。但Internet的复杂性、可访问性和开放性带来了日益增长的严重的信息系统安全的威胁。论文介绍了一种使用支持向量机和神经网络的入侵监测系统。主要思想是发现用以描述用户在系统上行为的模式与特征,用一系列相关的特征建立分类器去进行异常检测,希望能够实时地发现入侵。通过比较基于神经网络和支撑向量机的入侵检测系统,利用两者各自的优势,构造了一种新的入侵检测系统。
Information security is an issue of serious global concern.The complexity,accessibility,and openness of the Internet have served to increase the security risk of information systems tremendously.This paper describes a intrusion detection system using neural networks and support vector machines.The key ideas are to discover useful patterns or features that describe user behavior on a system,and use the set of relevant features to build classifiers that can recog-nize anomalies and known intrusions,hopefully in real time.We compare intrusion detection systems of neural networks based and support vector machine based,and build a new intrusion detection system using the advantages of both.
出处
《计算机工程与应用》
CSCD
北大核心
2003年第26期24-27,共4页
Computer Engineering and Applications
基金
国家自然科学基金资助(编号:60074025)
