面向社会安全事件的分布式神经网络攻击行为分类方法

doi:10.11772/j.issn.1001-9081.2017.10.2794

计算机应用 ›› 2017, Vol. 37 ›› Issue (10): 2794-2798.DOI: 10.11772/j.issn.1001-9081.2017.10.2794

面向社会安全事件的分布式神经网络攻击行为分类方法

肖圣龙¹, 陈昕¹, 李卓^1,2

1. 北京信息科技大学计算机学院, 北京 100101;
2. 网络文化与数字传播北京市重点实验室, 北京 100101

收稿日期:2017-04-24 修回日期:2017-06-14 出版日期:2017-10-10 发布日期:2017-10-16
通讯作者: 陈昕(1965-),男,江西南昌人,教授,博士生导师,博士,CCF高级会员,主要研究方向:大数据分析、网络安全,E-mail:chenxin@bistu.edu.cn
作者简介:肖圣龙(1991-),男,福建莆田人,硕士研究生,主要研究方向:大数据分析、网络安全;陈昕(1965-),男,江西南昌人,教授,博士生导师,博士,CCF高级会员,主要研究方向:大数据分析、网络安全;李卓(1983-),男,河南南阳人,讲师,博士,CCF会员,主要研究方向:移动无线网络、分布式计算.
基金资助:
国家自然科学基金资助项目（61370065，61502040）；国家科技支撑计划项目（2015BAK12B00）。

Distributed neural network for classification of attack behavior to social security events

XIAO Shenglong¹, CHEN Xin¹, LI Zhuo^1,2

1. School of Computer Science, Beijing Information Science and Technology University, Beijing 100101, China;
2. Beijing Key Laboratory of Internet Culture and Digital Dissemination, Beijing 100101, China

Received:2017-04-24 Revised:2017-06-14 Online:2017-10-10 Published:2017-10-16
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61370065, 61502040), the National Key Technology Research and Development Program of the Ministry of Science and Technology of China (2015BAK12B00).

摘要/Abstract

摘要： 大数据时代下，社会安全事件呈现出数据多样化、数据量快速递增等特点，社会安全事件的事态与特性分析决策面临巨大的挑战。高效、准确识别社会安全事件中的攻击行为的类型，并为社会安全事件处置决策提供帮助，已经成为国家与网络空间安全领域的关键性问题。针对社会安全事件攻击行为分类，提出一种基于Spark平台的分布式神经网络分类算法（DNNC）。DNNC算法通过提取攻击行为类型的相关属性作为神经网络的输入数据，建立了各属性与攻击类型之间的函数关系并生成分布式神经网络分类模型。实验结果表明，所提出DNNC算法在全球恐怖主义数据库所提供的数据集上，虽然在部分攻击类型上准确率有所下降，但平均准确率比决策树算法提升15.90个百分点，比集成决策树算法提升8.60个百分点。

关键词: 社会安全, 大数据, Spark分布式系统, 神经网络, 分类算法

Abstract: In the era of big data, the social security data becomes more diverse and its amount increases rapidly, which challenges the analysis and decision of social security events significantly. How to accurately categorize the attack behavior in a short time and support the analysis and decision making of social security events becomes an urgent problem needed to be solved in the field of national and cyberspace security. Aiming at the behavior of aggression in social security events, a new Distributed Neural Network Classification (DNNC) algorithm was proposed based on the Spark platform. The DNNC algorithm was used to analyze the related features of the attack behavior categories, and the features were used as the input of the neural network. Then the function relationship between the individual features and attack categories were established, and a neural network classification model was generated to classify the attack categories of social security events. Experimental results on the data provided by the global terrorism database show that the proposed algorithm can improve the average accuracy by 15.90 percentage points compared with the decision tree classification, and by 8.60 percentage points compared with the ensemble decision tree classification, only decreases the accuracy on part attack type.

Key words: social security, big data, Spark distributed system, neural network, classification algorithm

中图分类号:

TP391.41

肖圣龙, 陈昕, 李卓. 面向社会安全事件的分布式神经网络攻击行为分类方法[J]. 计算机应用, 2017, 37(10): 2794-2798.

XIAO Shenglong, CHEN Xin, LI Zhuo. Distributed neural network for classification of attack behavior to social security events[J]. Journal of Computer Applications, 2017, 37(10): 2794-2798.

参考文献

[1] 国务院. 国家突发公共事件总体应急预案[J]. 中国中医基础医学杂志, 2006, 12(1):77-79.(State Council. National emergency response plan for public emergencies [J]. Chinese Journal of Basic Medicine in Traditional Chinese Medicine,2006, 12(1):77-79.)
[2] 孙越恒, 王文俊, 迟晓彤, 等. 基于多维时间序列模型的社会安全事件关联关系挖掘与预测[J]. 天津大学学报 (社会科学版), 2016, 18(2): 97-102. (SUN Y H, WANG W J, CHI X T, et al. Correlation mining and prediction of social security events based on multi-dimensional time series model[J]. Journal of Tianjin University (Social Sciences), 2016, 18(2): 97-102.)
[3] BACKER D A, BHAVNANI R, HUTH P K. Peace and Conflict 2016[M]. Oxford: Routledge, 2016: 67.
[4] KLUCH S P, VAUX A. The non-random nature of terrorism: an exploration of where and how global trends of terrorism have developed over 40 years[J]. Studies in Conflict & Terrorism, 2016, 39(12): 1031-1049.
[5] SIVARAMAN R, SRINIVASAN S, CHANDRASEKERAN R M. Big data on terrorist attacks: an analysis using the ensemble classifier approach[EB/OL]. [2017-01-10]. http://edlib.net/2015/icidret/icidret2015042.pdf.
[6] 焦李成, 杨淑媛, 刘芳, 等. 神经网络七十年: 回顾与展望[J]. 计算机学报, 2016, 39(8): 1697-1716. (JIAO L C, YANG S Y, LIU F, et al. Seventy years beyond neural networks: retrospect and prospect [J]. Chinese Journal of Computers, 2016, 39(8): 1697-1716.)
[7] 刘畅. BP神经网络的权值快速计算法及其逼近性能分析[J]. 科技视界, 2016(11): 130-131. (LIU C. Fuzzy calculation method and approximation performance analysis of BP neural network [J]. Science & Technology View, 2016(11): 130-131.)
[8] SALEHIAN S, YAN Y. Comparison of spark resource managers and distributed file systems[C]//Proceedings of the 2016 IEEE International Conferences on Big Data and Cloud Computing, Social Computing and Networking, Sustainable Computing and Communications. Piscataway, NJ: IEEE, 2016: 567-572.
[9] LIU T, FANG Z, ZHAO C, et al. Parallelization of a series of extreme learning machine algorithms based on spark[C]//Proceedings of the 2016 IEEE/ACIS 15th International Conference on Computer and Information Science. Piscataway, NJ: IEEE, 2016: 1-5.
[10] FREILICH J D, LAFREE G. Measurement issues in the study of terrorism: introducing the special issue[J]. Studies in Conflict and Terrorism, 2016, 39(7/8): 569-579.
[11] MEIERRIEKS D, SCHNEIDER F. The short-and long-run relationship between the illicit drug business and terrorism[J]. Applied Economics Letters, 2016, 23(18): 1274-1277.
[12] LUTZ B J, LUTZ J M. Globalization, terrorism, and the economy[M]//LUTZ B J, LUTZ J M. Globalization and the Economic Consequences of Terrorism. Berlin: Springer, 2017: 1-30.
[13] SAKHARE N N, JOSHI S A. Classification of criminal data using J48-decision tree algorithm[J]. IFRSA International Journal of Data Warehousing & Mining, 2014, 4(3): 167-171.
[14] SAKHARE N, JOSHI S. Criminal identification system based on data mining[C]//Proceedings of the 3rd International Conference on Recent Trends in Engineering and Technology. Chandwad, Nashik, India: [s.n.], 2014.
[15] JOSHI S, SAKHARE N. History bits based novel algorithm for classification of structured data[C]//Proceedings of the 2015 IEEE International Advance Computing Conference. Piscataway, NJ: IEEE, 2015: 609-612.
[16] SHEIKH H R. Use of predictive modeling for prediction of future terrorist attacks in Pakistan[EB/OL]. [2017-01-10]. http://koha.isra.edu.pk: 8080/jspui/handle/123456789/59.
[17] WU S, LIU Q, BAI P, et al. SAPE: a system for situation-aware public security evaluation[C]//Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence. Menlo Park: AAAI Press, 2016: 4401-4402.
[18] STRANG K D, SUN Z. Analyzing relationships in terrorism big data using Hadoop and statistics[J]. Journal of Computer Information Systems, 2017, 57(1): 67-75.
[19] DEAN J, GHEMAWAT S. MapReduce: simplified data processing on large clusters[J]. Communications of the ACM, 2008, 51(1): 107-113.
[20] LÄMMEL R. Google's MapReduce programming model-revisited[J]. Science of Computer Programming, 2008, 70(1): 1-30.
[21] ZAHARIA M, CHOWDHURY M, FRANKLIN M J, et al. Spark: cluster computing with working sets[C]//HotCloud 2010: Proceedings of the 2nd USENIX Conference on Hot Topics in Cloud Computing. Berkeley: USENIX Association, 2010: 10.
[22] ZAHARIA M, CHOWDHURY M, DAS T, et al. Resilient distributed datasets: a fault-tolerant abstraction for in-memory cluster computing[C]//Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation. Berkeley: USENIX Association, 2012: 2.
[23] MENG X, BRADLEY J, YUVAZ B, et al. MLlib: machine learning in Apache Spark[J]. The Journal of Machine Learning Research, 2016, 17(1): 1235-1241.

面向社会安全事件的分布式神经网络攻击行为分类方法

Distributed neural network for classification of attack behavior to social security events

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	刘子辰, 李小娟, 韦伟. 基于循环神经网络的专利价格自动评估[J]. 计算机应用, 2021, 41(9): 2532-2538.
[2]	宋中山, 梁家锐, 郑禄, 刘振宇, 帖军. 基于双向门控尺度特征融合的遥感场景分类[J]. 计算机应用, 2021, 41(9): 2726-2735.
[3]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[4]	张永斌, 常文欣, 孙连山, 张航. 基于字典的域名生成算法生成域名的检测方法[J]. 计算机应用, 2021, 41(9): 2609-2614.
[5]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[6]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[7]	牟长宁, 王海鹏, 周丕宇, 侯鑫行. 基于图卷积神经网络的串联质谱从头测序[J]. 计算机应用, 2021, 41(9): 2773-2779.
[8]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[9]	丁尹, 桑楠, 李晓瑜, 吴飞舟. 基于循环神经网络的电信行业容量数据预测方法[J]. 计算机应用, 2021, 41(8): 2373-2378.
[10]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[11]	黄程程, 董霄霄, 李钊. 基于二维Winograd算法的深流水线5×5卷积方法[J]. 计算机应用, 2021, 41(8): 2258-2264.
[12]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[13]	曾祥银, 郑伯川, 刘丹. 基于深度卷积神经网络和聚类的左右轨道线检测[J]. 计算机应用, 2021, 41(8): 2324-2329.
[14]	武光利, 李雷霆, 郭振洲, 王成祥. 基于改进的双向长短期记忆网络的视频摘要生成模型[J]. 计算机应用, 2021, 41(7): 1908-1914.
[15]	高钦泉, 黄炳城, 刘文哲, 童同. 基于改进CenterNet的竹条表面缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1933-1938.