基于改进的ART-2神经网络的IDS的设计  

Design of Intrusion Detection System Based on Modified ART-2 Neural Network

作　　者：李德峰[1] 柴乔林[1] 马福强[1] 

机构地区：[1]山东大学计算机科学与技术学院,济南250061

出　　处：《计算机工程》2005年第7期158-159,192,共3页Computer Engineering

摘　　要：提出了一种基于改进的ART-2神经网络的入侵检测系统,采用新的非线性变换函数和竞争层学习算法克服了ART-2神经网络的“预处理信号畸变”和“同相位不可分”问题,使之更适用于入侵检测,提高了检测的准确率和对未知入侵的自适应识别能力。The paper presents a new intrusion detection system based on modified ART-2 neural network, adopts new non-linear transfer function and competitive learning algorithm to solve the problem that the same phasic data with different amplitude can't be distinguished by the standard ART-2 neural network and make it more suitable for intrusion detection system. It can raise the accuracy of detection and the ability of adaptively detecting unknown intrusion.

关 键 词：入侵检测系统 自适应共振 神经网络 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]