混合多层结构化网络攻击态势预测算法仿真  

Simulation of Attack Situation Prediction Algorithms for Hybrid Multilayer Structured Networks

作　　者：张曼[1] ZHANG Man(Northwest University of Political Science and Law,Xian Shanxi 710100,China)

机构地区：[1]西北政法大学,陕西西安710100

出　　处：《计算机仿真》2021年第3期487-491,共5页Computer Simulation

摘　　要：为了提高网络攻击态势预测的准确性,提出混合多层结构化网络攻击态势预测算法。首先要在入侵检测系统报警综合评估中,获取网络攻击态势指标,然后通过支持向量机的预测算法,运用过去和当前网络攻击态势值,对网络攻击态势评估指标进行时间序列预测,并利用遗传算法对支持向量机做参数优化处理,增强了网络攻击态势的预测速度,最后由训练模块及预测模块结构来实现网络攻击态势预测。根据仿真对预测算法精度进行检验,实验结果表明,预测算法能够准确描绘网络攻击整体变化趋势,提高了网络攻击态势的预测准确性,适用于现实的网络环境中。In order to improve the accuracy of predicting network attack situation,an algorithm of predicting attack situation of mixed multi-layer structured network was proposed.Firstly,it was necessary to get network attack situation indexes in the comprehensive evaluation of intrusion detection system.Then,we used the prediction algorithm of support vector machine and the past and current values of network attack situation to predict the time series of assessment indexes of network attack situation.Meanwhile,we used genetic algorithm to optimize the parameters of support vector machine,so as to increase the prediction speed of network attack situation.Finally,we realized the situation prediction of network attack based on the structure of training module and prediction module.Simulation results show that the proposed algorithm can accurately describe the overall trend of network attack,and improve the accuracy of predicting network attack situation.

关 键 词：网络攻击态势 检测系统 支持向量机 参数优化 训练模块 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]