《计算机应用研究》|Application Research of Computers

一种基于复杂网络的网络安全态势预测机制

Network security situation prediction mechanism based on complex network

免费全文下载 (已被下载 次)  
获取PDF全文
作者 李方伟,邓武,朱江
机构 重庆邮电大学 移动通信技术重庆市重点实验室,重庆 400065
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2015)04-1141-04
DOI 10.3969/j.issn.1001-3695.2015.04.043
摘要 针对现有态势预测方法大都是对态势值的预测,并未揭示网络态势要素动力学特征的问题,提出了一种基于复杂网络的网络安全态势预测机制,可方便而又直观地追溯安全态势中数值波动的动力学特征。其次在该机制中提出基于复杂网络的马尔可夫预测方法,实现对安全状态的有效预测。通过仿真实验分析,该机制在一定程度上能突出系统的本质行为,且能较准确地预测未来的安全状态。
关键词 网络安全;态势预测;复杂网络;马尔可夫模型;动力学特征
基金项目 国家自然科学基金资助项目(61271260)
本文URL http://www.arocmag.com/article/01-2015-04-043.html
英文标题 Network security situation prediction mechanism based on complex network
作者英文名 LI Fang-wei, DENG Wu, ZHU Jiang
机构英文名 Chongqing Key Laboratory of Mobile Communications Technology, Chongqing University of Posts & Telecommunications, Chongqing 400065, China
英文摘要 For most current forecast methods only focusing on the prediction of situation value and not revealing the problem of dynamics features of the network situational factors, this paper proposed a complex network based network security situation prediction mechanism. The mechanism was convenient and intuitive to trace dynamics behavior of the numerical fluctuations in the security situation. In addition, in order to predict security state, the thesis proposed Markov prediction method based on complex network. Through simulation analysis, the mechanism can reflect the essential condition of the system in a certain extent and predict the future security status more accurately.
英文关键词 network security; situation prediction; complex network; Markov model; dynamical characteristics
参考文献 查看稿件参考文献
  [1] BASS T, GRUBER D. A glimpse into the future of ID[EB/OL] . (1999). http://www. usenix. org/publications/login/1999/29/features/future. html.
[2] 李凯, 曹阳. 基于ARIMA模型的网络安全威胁态势预测方法[J] . 计算机应用研究, 2012, 29(8):3042-3045.
[3] MAN Da-peng, WANG Yan, WU Yong, et al. A combined prediction method for network security situation[C] //Proc of International Conference on Computational Intelligence and Software Engineering. [S. l. ] :IEEE Press, 2010:1-4.
[4] DONG Jian-feng. The building of network security situation evaluation and prediction model based on grey theory[C] //Proc of International Conference on Challenges in Environmental Science and Computer Engineering. [S. l. ] :IEEE Press, 2010:401-404.
[5] 卓莹, 张强, 龚正虎. 网络态势预测的广义回归神经网络模型[J] . 解放军理工大学学报:自然科学版, 2012, 13(2):147-151.
[6] CHEN Jun, TU Xiong-gang. Network security risk assessment based on support vector machine[C] //Proc of the 3rd IEEE International Conference on Communication Software and Networks. [S. l. ] :IEEE Press, 2011:184-187.
[7] 朱丽娜, 张作昌, 冯力. 层次化网络安全威胁态势评估技术研究[J] . 计算机应用研究, 2011, 28(11):4303-4306, 4310.
[8] 赖积保. 基于异构传感器的网络安全态势感知若干关键技术研究[D] . 哈尔滨:哈尔滨工业大学, 2009.
[9] 陈秀真, 郑庆华, 管晓宏, 等. 层次化网络安全威胁态势量化评估方法[J] . 物理学报, 2006, 17(4):885-887.
[10] 向馗, 蒋静坪. 时间序列的符号化研究[J] . 模式识别与人工智能, 2007, 20(2):154-161.
[11] 陈卫东, 徐华, 郭琦. 国际石油价格复杂网络的动力学拓扑性质[J] . 物理学报, 2010, 59(7):4514-4523.
[12] 周磊, 龚志强, 支蓉, 等. 利用复杂网络研究中国温度序列的拓扑性质[J] . 物理学报, 2008, 57(11):7380-7389.
[13] 高湘峋, 安海忠, 方伟. 基于复杂网络的时间序列双变量相关性波动研究[J] . 物理学报, 2012, 61(9):1-9.
[14] 汪小帆, 李翔, 陈关荣. 复杂网络理论及应用[M] . 北京:清华大学出版社, 2006.
[15] 樊平毅. 随机过程理论与应用[M] . 北京:清华大学出版社, 2005.
收稿日期 2014/4/3
修回日期 2014/5/30
页码 1141-1144
中图分类号 TP393.08
文献标志码 A