SDN环境下基于BP神经网络的DDoS攻击检测方法

DDo S attack detection based on BPNN in software defined networks

软件定义网络是一种全新的网络架构,集中控制是其主要优势,但若受到DDo S攻击则会造成信息不可达,也容易造成单点失效。为了有效地识别DDo S攻击,提出了一种SDN环境下基于BP神经网络的DDo S攻击检测方法。该方法获取Open Flow交换机的流表项,分析SDN环境下DDo S攻击特性,提取出与攻击相关的流表匹配成功率、流表项速率等六个重要特征;通过分析六个相关特征值的变化,采用BP神经网络算法对训练样本进行分类,实现对DDo S攻击的检测。实验结果表明,该方法在有效提高识别率的同时,降低了检测时间。通过在软件定义网络环境中的部署,验证了该方法的有效性。

Software definition network is a new network architecture that achieves a centralized network control.Although centralized control is the main advantage of SDN,but if subject to DDoS attacks,the information will be not reachable,it also likely to cause a single point of failure.In order to mitigate this threat,this paper proposed a DDoS attack detection method based on SDN centralized control.This algorithm obtained the flow table items of OpenFlow switch,analyzed the characteristics of DDoS attacks in SDN environment,and extracted six characteristics related to attacks.By analyzing the changes of the six eigenvalues,it used BP neural network algorithm to classify the training samples to achieve the DDoS attack detection.The experimental results show that the method can improve the recognition rate and reduce the detection time.The effectiveness of the method is verified by the deployment in a software-defined network environment.