关于网络中入侵节点信息优化检测仿真研究
发布时间：2018-11-12 08:56
【摘要】：对网络中入侵节点信息进行优化检测,能够更好的保障网络安全稳定运行。对入侵节点信息检测时,需要根据节点的最佳获取路径,得到SVM的最优参数,来完成对入侵节点信息的检测。传统方法利用蚁群寻觅网络节点路径,得到支持向量机参数,但忽略了该参数的最优化,导致对信息的检测结果不准确。提出基于属性攻击图的入侵节点信息优化检测方法。定义网络潜质入侵的属性攻击图,将具有入侵节点信息的复杂入侵信号分解为IMF单频入侵信号,获取网络入侵检测系统的状态转移方程,将蚁群理论和支持向量机参数相融合,将网络入侵检查率作为目标函数,并对蚂蚁进行高斯异变,将最优路径上的节点连接起来得到SVM最优参数,以参数为依据完成对网络入侵节点信息检测。实验证明,所提方法设计精确度高,可以有效的提升嵌入式计算机网络入侵检测精度。
[Abstract]:The detection of intrusion node information in the network can better ensure the safe and stable operation of the network. In the detection of intrusion node information, the optimal parameters of SVM should be obtained according to the optimal access path of the node to complete the detection of the intrusion node information. The traditional method uses ant colony to search the path of network nodes to obtain the support vector machine parameters, but the optimization of the parameters is ignored, which leads to inaccurate information detection results. An intrusion node information detection method based on attribute attack graph is proposed. The attribute attack graph of network potential intrusion is defined, the complex intrusion signal with intrusion node information is decomposed into IMF single frequency intrusion signal, the state transition equation of network intrusion detection system is obtained, and the ant colony theory and support vector machine parameters are fused. The network intrusion detection rate is taken as the objective function, and the ant is changed by Gao Si, and the nodes on the optimal path are connected together to obtain the optimal parameters of SVM, and the information of the network intrusion node is detected based on the parameters. Experiments show that the proposed method has high design accuracy and can effectively improve the accuracy of embedded computer network intrusion detection.
【作者单位】： 全球能源互联网研究院;
【基金】：国家电网公司2015年科技项目(SGRIXTKJ【2015】614)
【分类号】：TP393.08
，
本文编号：2326651
[Abstract]:The detection of intrusion node information in the network can better ensure the safe and stable operation of the network. In the detection of intrusion node information, the optimal parameters of SVM should be obtained according to the optimal access path of the node to complete the detection of the intrusion node information. The traditional method uses ant colony to search the path of network nodes to obtain the support vector machine parameters, but the optimization of the parameters is ignored, which leads to inaccurate information detection results. An intrusion node information detection method based on attribute attack graph is proposed. The attribute attack graph of network potential intrusion is defined, the complex intrusion signal with intrusion node information is decomposed into IMF single frequency intrusion signal, the state transition equation of network intrusion detection system is obtained, and the ant colony theory and support vector machine parameters are fused. The network intrusion detection rate is taken as the objective function, and the ant is changed by Gao Si, and the nodes on the optimal path are connected together to obtain the optimal parameters of SVM, and the information of the network intrusion node is detected based on the parameters. Experiments show that the proposed method has high design accuracy and can effectively improve the accuracy of embedded computer network intrusion detection.
【作者单位】： 全球能源互联网研究院;
【基金】：国家电网公司2015年科技项目(SGRIXTKJ【2015】614)
【分类号】：TP393.08
，
本文编号：2326651
本文链接：https://www.wllwen.com/guanlilunwen/ydhl/2326651.html
