2022年 05期

摘要(Abstract)：

针对网络异常流量检测技术准确率较低、簇的误划分等问题，提出基于改进密度峰值聚类算法的网络异常流量检测方案；首先对网络流量数据进行预处理和分组乱序，然后计算相应属性值并利用局部密度发现簇中心点，最后采用一种新的标签传递方式形成相应的簇群直至处理完所有数据。结果表明，相对于k均值算法和具有噪声的基于密度的聚类算法，基于改进的密度峰值聚类算法提升了网络异常流量的检测准确率，综合性能较优。

关键词(KeyWords)： 网络安全;异常流量检测;聚类;密度峰值;局部密度

基金项目(Foundation): 国家自然科学基金项目(61966033);; 新疆维吾尔自治区高等学校科研计划项目(XJEDU2019Y036);; 新疆维吾尔自治区社会科学基金项目(19BTJ037);; 新疆财经大学校级科研基金项目(2020XYB004)

作者(Author): 任艳,徐春,张蕾,汪晓洁

DOI: 10.13349/j.cnki.jdxbn.20220526.004

参考文献(References)：

[1] 马广頔.社交媒体异常用户检测关键技术研究[D].哈尔滨：哈尔滨工程大学，2018.

[2] 张婷.基于机器学习的网络异常流量检测研究[D].北京：北京邮电大学，2020.

[3] SOMMER R,PAXSON V.Outside the closed world:on using machine learning for network intrusion detection[C]//2010 IEEE Symposium on Security and Privacy,May 16-19,2010,Oakland,USA.New York:IEEE,2010:305-316.

[4] SRINIVASA MURTHY Y V,HARISH K,VISHAL VARMA D K,et al.Hybrid intelligent intrusion detection system using Bayesian and genetic algorithm(BAGA):comparitive study[J].International Journal of Computer Applications,2014,99(2):1-8.

[5] 胡明霞.基于BP神经网络的入侵检测算法[J].计算机工程，2012,38(6):148-150.

[6] AGYEMANG M,BARKER K,ALHAJJ R.A comprehensive survey of numeric and symbolic outlier mining techniques[J].Intelligent Data Analysis,2006,10(6):521-538.

[7] RAWASHDEH A,RAWASHDEH M,DíAZ I,et al.Measures of semantic similarity of nodes in a social network[C]//LAURENT A,STRAUSS O,BOUCHON-MEUNIER B,et al.Information Processing and Management of Uncertainty in Knowledge-based Systems(IPMU 2014).Communications in Computer and Information Science,Vol 443.Cham:Springer,2014:76-85.

[8] 杨茂林.离群检测算法研究[D].武汉：华中科技大学，2012.

[9] XU J H,LIU H.Web user clustering analysis based on KMeans algorithm[C]//2010 International Conference on Information,Networking and Automation (ICINA),October 18-19,2010,Kunming,China.New York:IEEE,2010:6-9.

[10] 李佳玮，吴克河，张波.基于高斯混合聚类的电力工控系统异常检测研究[J].信息网络安全，2021,21(3):53-63.

[11] YANG Y C,WANG Y P,WEI Y.Adaptive density peak clustering for determinging cluster center[C]//2019 15th International Conference on Computational Intelligence and Security(CIS),December 13-16,2019,Macao,China.New York:IEEE,2019:182-186.

[12] DU H,NI Y Y.The improvement on self-adaption select cluster centers based on fast search and find of density peaks clustering[C]//2020 16th International Conference on Computational Intelligence and Security(CIS),November 27-30,2020,Nanning,China.New York:IEEE,2020:234-237.

[13] WU C R,LEE J,ISOKAWA T,et al.Efficient clustering method based on density peaks with symmetric neighborhood relationship[J].IEEE Access,2019,7:60684-60696.

[14] KAMALI T,STASHUK D W.Discovering density-based clustering structures using neighborhood distance entropy consistency[J].IEEE Transactions on Computational Social Systems,2020,7(4):1069-1080.