通信网络用户涉密信息安全动态预警仿真  

Dynamic Early Warning Simulation of Classified Information Security for Communication Network Users

作　　者：王梦晓 刘学军[2] 操凤萍[1] WANG Meng-xiao;LIU Xue-jun;CAO Feng-ping(Southeast University,Chenxian College,Southeast University,Nanjing Jinagsu 210088,China;School of Computer Science,Nanjing University of Aeronautics and Astronautics,Nanjing Jiangsu 211106,China)

机构地区：[1]东南大学成贤学院,江苏南京210088 [2]南京航空航天大学计算机学院,江苏南京211106

出　　处：《计算机仿真》2023年第5期422-425,476,共5页Computer Simulation

基　　金：航空科学基金(2019ZA052011);2021年度高校哲学社会科学研究一般项目(2021SJA2234)。

摘　　要：大规模通信网络部署难度大,网络运维复杂,易产生安全漏洞造成通信用户双方身份信息的泄露。为实现大规模通信网络用户个人通信隐私及对涉密通信更好的保护,提出大规模通信网络涉密信息安全动态预警算法。算法首先采用模糊聚类法处理网络涉密信息,得到相应的特征流量。其次根据样本估计理论确定出具有异常状态的特征流量区域。最后采取妥协率法构建决策者模型,通过对异常特征流量的风险要素排序,完成大规模通信网络涉密信息安全的动态预警。通过实验对比测试可知,上述方法的涉密信息安全动态预警耗时平均为12.47ms,准确率高于90%,误报率可控制在5%以下。以上数据证明了所提出的方法应用性能具有明显优势。。In order to better protect user privacy in large-scale communication networks and classified communication,a dynamic early-warning algorithm for classified information security in large-scale communication networks was presented.Firstly,we used the fuzzy clustering method to process the secret information,thus obtaining characteristic traffic correspondingly.Secondly,we used the sample estimation theory to determine the characteristic flow region with abnormal states.Finally,the compromise rate method was used to build a decision-maker model.After sorting the risk factors of abnormal characteristic traffic,we completed the dynamic early warning for classified information in large-scale communication networks.Through the experimental comparison,it can be concluded that the time consumption of dynamic early warning is 12.47ms on average,and the accuracy rate is higher than 90%.Meanwhile,the false alarm rate of the method can be controlled within 5%.The above data prove that the application performance of the proposed method has obvious advantages.

关 键 词：信息模糊聚类 固定阈值 拉格朗日函数 样本估计理论 决策者模型 

分 类 号：TP393.01[自动化与计算机技术—计算机应用技术]