一种改进Kohonen网络的DoS攻击检测算法

发布时间：2018-05-14 08:04

本文选题：S-Kohonen网络 + DoS　；参考：《小型微型计算机系统》2017年03期

【摘要】：拒绝服务(Denial of Service,DoS)是企图使其预期用户的一台主机或其他网络资源不可用,如临时或无限期地中断或暂停连接到因特网主机的服务.为了有效地阻止DoS攻击,首先需要提高DoS攻击检测的准确性,提出一种基于改进Kohonen网络的DoS攻击检测算法.该方法通过对DoS攻击原始数据的预处理,为后续数据处理的方便和保证程序运行时加快收敛奠定必要的基础,采用检测结果的正确率作为该算法的评价指标,采用SOM学习算法是把高维空间的输入数据映射到低维神经网络上,并且保持原来的拓扑次序,然后建立S-Kohonen(Supervised-Kohonen)神经网络检测模型.实验结果表明,与传统的Kohonen方法相比,S-Kohonen网络具有更好的检测性能.
[Abstract]:Denial of Service (dos) is an attempt to disable a host or other network resource of its intended user, such as temporarily or indefinitely interrupting or suspending services connected to an Internet host. In order to effectively prevent DoS attacks, it is necessary to improve the accuracy of DoS attack detection. A DoS attack detection algorithm based on improved Kohonen network is proposed. By preprocessing the raw data of DoS attack, the method lays a necessary foundation for the convenience of the subsequent data processing and the guarantee of program convergence. The correct rate of the detection result is used as the evaluation index of the algorithm. The SOM learning algorithm is used to map the input data of the high-dimensional space to the low-dimensional neural network and maintain the original topological order. Then the S-Kohonenn Supervised-Kohonen neural network detection model is established. The experimental results show that the S-Kohonen network has better detection performance than the traditional Kohonen method.
【作者单位】：河北大学电子信息工程学院;
【基金】：国家科技支撑计划项目(2013BAK07B04)资助国家自然基金项目(61672205)资助河北省自然科学基金项目(F2013201170)资助河北省高等学校科学技术研究重点项目(ZD2014008)资助
【分类号】：TP393.08

【相似文献】