摘要
针对目前大多数的入侵检测系统存在的局限性,提出一种较完善的入侵检测模型,将专家系统和神经网络技术同时应用于入侵检测系统中.设计专家系统模块检测已知攻击,设计神经网络模块实现未知攻击的检测,提高了检测准确性.同时在神经网络模块应用PCA方法降低入侵数据维数,提高检测效率.仿真实验验证,该设计能有效降低入侵检测系统的漏报率和误报率.
Aimed at the limitation of most intrusion detection systems, this paper proposes a more perfect IDS, expert system and neural network are applied in IDS. Designed the ES module to detect the known attack, the ANN module detect the unknown attack. This can improve the rate of correction. Using the PCA to reduce the dimension of the data, it can improve the efficiency of the detection. The design reduces the rate of failure statement and misstatement by simulation.
出处
《数学的实践与认识》
CSCD
北大核心
2009年第6期162-169,共8页
Mathematics in Practice and Theory
关键词
入侵检测系统
专家系统
神经网络
特征提取
intrusion detection system
expert system
neural network
feature extraction
