基于智能蜂群算法的DDoS攻击检测系统

随着大数据应用的普及,DDoS攻击日益严重并已成为主要的网络安全问题。针对大数据环境下的DDoS攻击检测问题,设计了一种融合聚类和智能蜂群算法(DFSABC_elite)的DDoS攻击检测系统。该系统将聚类算法与智能蜂群算法相结合来进行数据流分类,用流量特征分布熵与广义似然比较判别因子来检测DDoS攻击数据流的特征,从而实现了DDoS攻击数据流的高效检测。实验结果显示,该系统在类内紧密度、类间分离度、聚类准确率、算法耗时和DDoS检测准确率方面明显优于基于并行化K-means的普通蜂群算法和基于并行化K-means算法的DDoS检测方法。

DDoS Attack Detection System Based on Intelligent Bee Colony Algorithm

With the popularity of the applications of big data,DDoS attacks become increasingly serious and have been the main network security issues.This paper designed a DDoS attack intrusion detection system based on clustering and intelligent bee colony algorithm (DFSABC_elite) for DDoS attack detection in environment of big data.The system combines the clustering algorithm and the intelligent bee colony algorithm to classify DDoS attack data flow,and uses the traffic feature distribution entropy and the generalized likelihood comparison distinguishing factor together to detect the characteristics of DDoS attack data stream,thus achieving the efficient detection of DDoS attack data flow.Experimental results show that this system is obviously superior to the ordinary bee colony algorithm based on parallelization K-means and the DDOS detection algorithm based on parallelization K-means in terms of intra-class compactness,inter-class separation,clustering accuracy,consumed time and DDoS detection accuracy.