基于交叉覆盖算法的入侵检测  

The Intrusion Detection Based on The Alternative Covering Algorithm

作　　者：赵姝[1] 张燕平[1] 张媛[1] 陈传明[1] 

机构地区：[1]安徽大学人工智能研究所智能计算与信号处理重点实验室,合肥230039

出　　处：《计算机工程与应用》2005年第1期141-143,共3页Computer Engineering and Applications

基　　金：国家自然科学基金(编号:60175018);安徽省教育厅自然科学研究基金(编号:2003kj007)的资助

摘　　要：文章提出了一种应用人工神经网络进行入侵检测分类器设计的新方法,即采用多层前向网络的交叉覆盖算法进行入侵检测分类器的设计。该算法克服了传统BP算法的收敛速度慢,易陷入局部最小点的问题。实验结果表明,该分类器用于入侵检测,效果良好,学习速度快,分类准确率高,为实现入侵检测分类器提供了一条准确高效的途径。A new method of designing the classifier for intrusion detection is proposed based on neural networks,which is the alternative covering algorithm of multi-layer neural networks.The algorithm solved the problems of the conventional BP algorithm such as converging slowly and falling into the local minimum point easily.The experimental result shows that the performance of the classifier for intrusion detection is favorable,the learning speed of the classifier is fast,and the rate of accurate classification is high.The networks provide a precise and efficient way for implementing the classifier in intrusion detection.

关 键 词：交叉覆盖算法 入侵检测 神经网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]