[1]钟 磊,何恒宏,韩春阳,等.基于机器学习的气象网络数据安全研究[J].计算机技术与发展,2021,31(09):161-166.[doi:10. 3969 / j. issn. 1673-629X. 2021. 09. 027]
　ZHONG Lei,HE Heng-hong,HAN Chun-yang,et al.Research on Data Security of Meteorological Network Based on Machine Learning[J].,2021,31(09):161-166.[doi:10. 3969 / j. issn. 1673-629X. 2021. 09. 027]
点击复制

基于机器学习的气象网络数据安全研究()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
31
期数:
2021年09期
页码:
161-166
栏目:
应用前沿与综合
出版日期:
2021-09-10

文章信息/Info

Title:
Research on Data Security of Meteorological Network Based on Machine Learning
文章编号:
1673-629X(2021)09-0161-06
作者:
钟 磊; 何恒宏; 韩春阳; 李 楠
国家气象信息中心,北京 100081
Author(s):
ZHONG Lei; HE Heng-hong; HAN Chun-yang; LI Nan
National Meteorological Information Center,Beijing 100081,China
关键词:
Louvain 算法; TF-IDF; 逻辑回归; 机器学习; 气象数据安全
Keywords:
Louvain algorithm; TF-IDF; logistic regression; machine learning; meteorological data security
分类号:
TP302. 1
DOI:
10. 3969 / j. issn. 1673-629X. 2021. 09. 027
摘要:
随着气象信息化的不断推进,气象网络和数据安全面临新的挑战:气象业务系统需要进行针对性安全加固,安全防护体系在策略和部署方式方面也需要优化。 现阶段,气象网络安全防护和自动化加固程度不高,依赖人工进行分析和处理。 当信息数量庞大和种类繁杂时,运维效率较低且安全加固效果无法直观的核验。 该文以不同业务区域的安全检测数据为基础,首先采用 Louvain 算法生成不同业务系统的数据交互结构,对系统存在的安全风险进行定位;随后通过 TF-IDF 算法和逻辑回归算法对网络数据日志进行分析,获取安全事件中的核心内容,结合系统数据交互结构对存在安全风险的系统进行针对性加固;最后通过对比研究前后安全事件数量上的变化,验证有关研究和算法的合理性。
Abstract:
With the continuous advancement of meteorological informatization,meteorological networks and data security are facing new challenges. The meteorological service systems need to be targeted for security hardening, and the security protection systems need to be optimized in terms of strategy and deployment. At present,the degree of meteorological network security protection and automation reinforcement is not high,relying on manual analysis and processing. When the amount of information is huge and the types are complex, the operation and maintenance efficiency is low and the security reinforcement effect cannot be intuitively verified. Based on security inspection data from different business areas,firstly the Louvain algorithm is used to generate the data interaction structure of different business systems,so as to locate the security risks existing in the system. Secondly,the TF-IDF algorithm and the logistic regression algorithm are used to analyze the network data log,obtain the core content in the security event,and perform targeted reinforcement on the system with security risks. Finally,the rationality of research and algorithm design is verified by comparing the number of security events before and after optimization.

相似文献/References:

[1]陈春玲,吴凡,余瀚.基于逻辑斯蒂回归的恶意请求分类识别模型[J].计算机技术与发展,2019,29(02):124.[doi:10．3969/j．issn．1673－629X．2019．02．026]
　CHEN Chunling,WU Fan,YU Han.A Classification and Recognition Model of Malicious Requests Based on Logistic Regression[J].,2019,29(09):124.[doi:10．3969/j．issn．1673－629X．2019．02．026]
[2]林江豪,顾也力,周咏梅,等.基于表情符号的情感词典的构建研究[J].计算机技术与发展,2019,29(06):181.[doi:10. 3969 / j. issn. 1673-629X. 2019. 06. 037]
　LIN Jiang-hao,GU Ye-li,ZHOU Yong-mei,et al.Research on Building Sentiment Lexicon Based on Emoticons[J].,2019,29(09):181.[doi:10. 3969 / j. issn. 1673-629X. 2019. 06. 037]
[3]伍 哲,杨 芳.时间加权的 TF-LDA 学术文献摘要主题分析[J].计算机技术与发展,2020,30(01):194.[doi:10. 3969 / j. issn. 1673-629X. 2020. 01. 035]
　WU Zhe,YANG Fang.A Thematic Analysis Method of Academic Documents Based on TF-IDF and LDA[J].,2020,30(09):194.[doi:10. 3969 / j. issn. 1673-629X. 2020. 01. 035]
[4]毛典辉,梁秀霞,赵 爽,等.面向区块链平台的庞氏骗局模式检测方法[J].计算机技术与发展,2022,32(05):153.[doi:10. 3969 / j. issn. 1673-629X. 2022. 05. 026]
　MAO Dian-hui,LIANG Xiu-xia,ZHAO Shuang,et al.Ponzi Scheme Pattern Detection Method for Blockchain Platform[J].,2022,32(09):153.[doi:10. 3969 / j. issn. 1673-629X. 2022. 05. 026]

更新日期/Last Update: 2021-09-10