摘要
入侵检测是一种积极主动的安全防护技术,不仅能够检测来自外部的入侵行为,同时也监督内部用户的未授权活动,有着非常广泛的应用前景。而人工神经网络是一种基于大量神经元广泛互联的数学模型,具有自学习、自组织、自适应的特点。将神经网络技术和入侵检测技术相结合,建立了一个基于神经网络的入侵检测系统模型并实现了一个基于BP(Back Propagation)神经网络的入侵检测系统的原形,对原有的误差返向传播算法进行了改进以提高收敛速度,然后对一些实际数据进行了测试和分析,在检测率、漏报率、误报率等方面取得了较好的效果。
Intrusion detection is a kind of active voluntary safe protection technique.IDS not only can detect intrusions from the outside,but also can supervise unauthorized users,has a very broad range of applications. Neural network is a mathematical model that has the characteristics of self-study,self-organization and self-adapting.Combined neural network with intrusion detecting technology, it builds the intrusion detection model based on BP algorithm to increase the performance of the original model, and gets good effectiveness.
出处
《重庆科技学院学报（自然科学版）》
CAS
2010年第1期157-159,162,共4页
Journal of Chongqing University of Science and Technology：Natural Sciences Edition
关键词
网络安全
入侵检测
神经网络
network security
intrusion detection
neural network
