基于并行约简的网络安全态势要素提取方法

发布时间：2018-04-14 12:06

  本文选题：网络安全态势 + 要素提取　； 参考：《计算机应用》2017年04期

【摘要】：网络安全态势要素选取的质量对网络安全态势评估的准确性起到至关重要的作用,而现有的网络安全态势要素提取方法大多依赖先验知识,并不适用于处理网络安全态势数据。为提高网络安全态势要素提取的质量与效率,提出一种基于属性重要度矩阵的并行约简算法,在经典粗糙集基础上引入并行约简思想,在保证分类不受影响的情况下,将单个决策信息表扩展到多个,利用条件熵计算属性重要度,根据约简规则删除冗余属性,从而实现网络安全态势要素的高效提取。为验证算法的高效性,利用Weka软件对数据进行分类预测,在NSL-KDD数据集中,相比利用全部属性,通过该算法约简后的属性进行分类建模的时间缩短了16.6%;对比评价指标发现,相比现有的三种态势要素提取算法(遗传算法(GA)、贪心式搜索算法(GSA)和基于条件熵的属性约简(ARCE)算法),该算法具有较高的召回率和较低的误警率。实验结果表明,经过该算法约简的数据具有更好的分类性能,实现了网络安全态势要素的高效提取。
[Abstract]:The quality of selecting network security situation elements plays an important role in the accuracy of network security situation assessment. However, most of the existing network security situation elements extraction methods rely on prior knowledge and are not suitable for dealing with network security situation data.In order to improve the quality and efficiency of network security situation extraction, a parallel reduction algorithm based on attribute importance matrix is proposed. The idea of parallel reduction is introduced on the basis of classical rough set.The single decision information table is extended to several, and the attribute importance is calculated by using conditional entropy, and the redundant attributes are deleted according to the reduction rules, so that the network security situation elements can be extracted efficiently.In order to verify the efficiency of the algorithm, we use Weka software to classify and predict the data. In the NSL-KDD data set, compared with the use of all attributes, the reduced attributes of the algorithm shorten the time of classification modeling.Compared with the three existing situational element extraction algorithms (genetic algorithm, greedy search algorithm, GSAs) and conditional entropy based attribute reduction algorithm, this algorithm has higher recall rate and lower false alarm rate.The experimental results show that the data reduced by this algorithm has better classification performance and can efficiently extract the network security situation elements.
，

本文编号：1749221