摘要
针对网络流量具有复杂的动力学特性,提出了一种应用自上而下的协同神经网络进行网络流量异常检测的方法.首先选择包含正常网络流量和异常攻击流量的数据集作为原型模式,然后通过协同神经网络进行序参量的动力演化,最终根据原型模式对应的序参量的演化结果来判定检测结果.实验结果证明,该方法能有效的识别出正常流量和异常攻击的种类.
For network traffic with complex dynamics characteristic, a method is proposed for network traffic anomaly detection, which based on a top-down synergetic neural network. First select the datasets that contain normal network traffic and abnormal attack traffic as a prototype pattern, and then calculate order parameter by synergetic neural network. Finally the detection result is obtained according to the evolution result of the order parameter corresponding to the prototype pattern in the end. Experimental results show that this method can effectively identify normal traffic and types of abnormal attacks.
出处
《华中师范大学学报（自然科学版）》
CAS
CSCD
北大核心
2012年第5期537-539,568,共4页
Journal of Central China Normal University：Natural Sciences
基金
中南民族大学校级基金项目(YZQ09006)
关键词
网络流量
异常检测
协同神经网络
序参量
network traffic
anomaly detection
synergetic neural network
order parameter
