非均匀分布入侵检测模型的研究与仿真

发布时间：2018-03-01 00:01

本文关键词： 入侵检测非均匀分布变异特征高斯分布　出处：《科技通报》2013年08期 　论文类型：期刊论文

【摘要】：网路入侵过程中入侵特征种类繁多,形成耦合性,很难形成较为规则的分布,传统的入侵检测方法都是假设网络入侵特征呈现独立高斯分布的,但是,一旦入侵特征耦合性较差,造成非高斯入侵数据拟合能力差,导致检测精度不理想。为了避免上述缺陷,提出了一种基于变异特征估计算法的非均匀分布入侵检测模型。在海量的网络操作数据中,提取出变异特征,根据提取的特征能够进行网络入侵检测。利用变异特征估计算法,能够建立合理的非均匀分布入侵检测模型,从而检测出网络入侵行为。实验结果表明,在非均匀分布的环境下,利用该算法对网络攻击行为进行检测,使非高斯数据具有更强的拟合能力,极大地降低了网络入侵检测的误报率和漏报率,提高了入侵检测的检测率。
[Abstract]:In the process of network intrusion, there are many kinds of intrusion features, forming coupling, so it is difficult to form a more regular distribution. Traditional intrusion detection methods assume that the network intrusion features are distributed independently of Gao Si, but, Once the coupling of intrusion features is poor, the fitting ability of non-#china_person0# intrusion data is poor, and the detection accuracy is not ideal. In order to avoid the above defects, In this paper, a non-uniform distributed intrusion detection model based on mutation feature estimation algorithm is proposed, in which variation features can be extracted from massive network operation data, and network intrusion detection can be carried out according to extracted features. A reasonable non-uniform distributed intrusion detection model can be established to detect the network intrusion behavior. The experimental results show that the algorithm is used to detect the network attack behavior in the non-uniform distributed environment. It makes the non-#china_person0# data have stronger fitting ability, greatly reduces the false alarm rate and false alarm rate of network intrusion detection, and improves the detection rate of intrusion detection.
【作者单位】：佛山广播电视大学教育技术实验中心;佛山科学技术学院信息与教育技术中心;
【基金】：广东省教育厅、佛山市、中央电大、省电大科研项目立项广东省电大远程教育开放基金项目(YJ1110)
【分类号】：TP393.08

【参考文献】