计算机网络安全评估与预测关键技术研究  

Research on Key Technologies of Computer Network Security Assessment and Prediction

作　　者：徐星辰 XU Xingchen(Party School of Huaining County Committee of the Communist Party of China,Anqing 246121,China;College of Information Science and Engineering,Ningbo University,Ningbo 315211,China)

机构地区：[1]中共怀宁县委党校 [2]宁波大学信息科学与工程学院

出　　处：《安阳师范学院学报》2019年第5期20-25,共6页Journal of Anyang Normal University

摘　　要：在当前的背景下,网络造福于普通大众的同时也给不法分子提供了更加高效的入侵手段,目前业内对于该领域的研究还不够充分,传统的方法也无法应对日益复杂化的网络安全环境。因此,本文首先分析了目前网络安全存在的问题;其次通过人工免疫方法建立了对网络安全状况的评估模型;再次,通过混合递阶算法结合RBF神经网络的手段来实现全局寻优以实现对于网络安全态势的准确预测,通过评估模型计算HoneyNet数据集中威胁数据所对应的安全态势值,并验证了所设计预测模型的有效性。实验结果表明,所设计的预测模型具有较高的预测精度。In the current situation,although the Internet communication rate and communication quality have reached a high level,the network also has an important seat in the social division of labor.While the Internet benefits the general public,it also provides criminals with more efficient means of intrusion.However,the current research in this field is not enough,and the traditional methods cannot cope with the increasingly complex network security environment.Therefore,this paper firstly analyzes the current problems of network security;secondly,it establishes an evaluation model of network security status through artificial immune method;again,through the hybrid hierarchical algorithm combined with RBF neural network to achieve global optimization and the accurate prediction of the network security situation,the security posture value corresponding to the threat data in the HoneyNet dataset is calculated by the evaluation model,and the validity of the designed prediction model is verified.The experimental results show that the designed prediction model has higher prediction accuracy.

关 键 词：安全态势 网络安全 量化评估 量化预测 

分 类 号：TP242.3[自动化与计算机技术—检测技术与自动化装置]