基于数据聚类的网络安全防护态势优化方法

Optimization method of network security protection situation based on data clustering

摘要:

针对传统的模糊特征检测方法不适应当前应用的问题,提出一种基于数据聚类的网络安全防护态势优化新方法。首先,构建网络安全状态分布模型,采用大数据挖掘方法对网络安全信息进行数据挖掘。其次,利用新型入侵识别检测方法对所设计的网络安全估计状态进行自适应特征提取,提取网络安全状况的特征数据集和处理单元。然后采用模糊C平均数据聚类方法(FCM)提取综合信息。对入侵特征信息流进行分类,根据属性分类结果进行网络安全态势预测,实现安全态势评估。最后基于不同场景下进行实验,结果表明,所提算法适用于网络安全的场景,准确性和鲁棒性都得到了验证。

Abstract:

Aiming at the problem that the traditional fuzzy feature detection method is not suitable for the current application, a new method of network security protection situation optimization based on data clustering is proposed. Firstly, a network security state distribution model is constructed, and the big data mining method is adopted to data mining network security information. Secondly, the new intrusion identification detection method is used to carry out adaptive feature extraction for the designed network security estimation state, and extract the characteristic data set and processing unit of the network security state. Then, fuzzy-C average data clustering method is used to extract comprehensive information. The intrusion characteristic information flow is classified, and the network security situation is predicted according to the attribute classification results to realize the security situation evaluation. Finally, experiments are carried out in different scenarios. The results show that the proposed algorithm is suitable for network security scenarios, and its accuracy and robustness are verified.