摘要
本文根据传统的入侵检测方法误报率高、U2R和R2L攻击检测率低等缺点,提出了一种基于神经网络多分类器组合的入侵检测方法。实验结果表明,该方法不仅能够有效地提高检测率,特别是U2R和R2L等攻击具有较好的检测能力。因此,本文提出的基于神经网络多分类器组合的入侵检测方法是有效和实用的。
According to the shortcomings of the traditional intrusion detection methods--high false positive rate, low detection rate to U2R and R2L attacks, this paper proposes an intrusion detection method based on neural network multiple classifiers combination. The results show that the method can effectively improve the detection rate, in particular, good detection capability to U2R and R2L attacks. Therefore, in this paper, the intrusion detection method based on neural network multiple classifiers combination is effective and practical.
出处
《微计算机信息》
2009年第24期59-61,共3页
Control & Automation
关键词
入侵检测
神经网络
多分类器组合
Intrusion Detection
Neural Network
Multiple Classifiers Combination
