融合多智能技术的网络入侵检测模型

网络入侵检测的关键问题是要使得检测准确率最大化,误警率最小化。为了解决这个问题,提出了集成多种智能学习范型的入侵检测模型。该模型融合了线性遗传规划,自适应神经模糊推理系统和随机森林学习算法。在分类前,使用两层的特征选择过程来约简特征,并在分别评估了每种学习算法的性能基础上,给出了融合规则。实验表明:融合多智能技术的入侵检测系统的性能要优于任何一个单一的分类器。

Network Intrusion Detection Model Integrated Multiple Intelligent Technologies

The key issue of network intrusion detection is to maximize accuracy and minimize false positive rate. In addressing this issue, this paper proposes a network intrusion detection model integrated multiple intelligent technologies. This model combines a linear genetic programming, adaptive neural-fuzzy inference system and random forest learning algorithm. Prior to classification, a 2-tier feature selection process was performed to expedite the detection process. Ensemble rule was formulated based on the evaluation of the strengths of each individual learning algorithm. Experimental results show that network intrusion detection model integrated multiple intelligent technologies is better than any single classifier.