Computer Engineering and Applications ›› 2008, Vol. 44 ›› Issue (28): 116-118.DOI: 10.3778/j.issn.1002-8331.2008.28.039

• 网络、通信、安全 • Previous Articles     Next Articles

DOS detection model in IMS based on GA neural network

WANG Xiao-lei,GUO Yun-fei,LI He   

  1. National Digital Switching System Engineering & Technological Research Center,Zhengzhou 450002,China
  • Received:2007-11-20 Revised:2008-02-26 Online:2008-10-01 Published:2008-10-01
  • Contact: WANG Xiao-lei

IMS中基于遗传神经网络的DOS攻击检测模型

王晓雷,郭云飞,李 贺   

  1. 国家数字交换系统工程技术研究中心,郑州 450002
  • 通讯作者: 王晓雷

Abstract: This paper first analyzes the specialty of DOS attack in IMS,and then proposes a DOS detection model applied in IMS based on GA neural network.The detection model uses GA to optimize the weights and biases of neural network.In the end,the paper makes a detection experiment using the data of kddcup99.The experiment shows that the detection probability of neural network with GA is much better than the model without GA.

Key words: IP Multimedia Subsystem(IMS), Denial of Service(DOS), neural network, Genetic Algorithm(GA)

摘要: 首先针对IMS中DOS攻击的特点进行了分析,然后基于遗传神经网络提出了一种应用于IMS的DOS攻击检测模型,在模型中利用遗传算法对神经网络的权值和偏置值进行优化。最后利用kddcup99数据集进行攻击检测实验。通过实验可以看出经过遗传算法优化后,神经网络的检测概率得到了明显提高。

关键词: IP多媒体子系统, DOS, 神经网络, 遗传算法