The existing customer project status recognition algorithm can not adaptively identify the tampering type and can not simultaneously identify the tampering of multiple project states, the algorithm of tampering recognition based on time series analysis is given. The PCA VarSelect algorithm is used to derive the suspicious list of project status and further reduce the recognition range. The method is to determine the tampering state according to the tampering time period and the score deviation degree.On this basis,this method can further analyze the tampering period of time to determine the type of tampering and finally identify the corresponding tampered state of the project. Simulation shows that the algorithm has high recognition accuracy.It not only can identify the tampering state of a single project, but also can identify the tampering state of multiple projects at the same time.
CHEN Chaofan
,
LIN Shuxin
. Customer project status tampering algorithm based on time series analysis[J]. Journal of Hebei University(Natural Science Edition), 2017
, 37(5)
: 545
-554
.
DOI: 10.3969/j.issn.1000-1565.2017.05.015
[1] BURKE R, MOBASHER B, WILLIAMs C, et al. Classification features for attack detection in collaborative recommender Systems[C] //Proceedings of the 12th ACM SIGKDD International Conference, ACM Press, 2006:542-547.
[2] CHIRITA P A, NEJDL W, ZAMFIR C. Preventing shilling attacks in online recommender systems[C] //Proceedings of The 7th annual ACM international workshop on Web information and data management, ACM Press, 2005:67-74.
[3] LEE J S, ZHU D. Shilling attack detection-A new approach for a trustworthy recommender system[J]. Informs Journal on Computing, 2011, 3(10): 1-15.
[4] SHI Z W, YANG S, JIANG Z G, et al. Hyperspectral target detection using regularized high-order matched filter[J].Optical Engineering,2011,50(5):057201-1-057201-10.
[5] MRHTA B, HOFMANN T, FANKHAUSER P. Lies and propaganda: detecting spam users in collaborative filtering[C] //Proceedings of The 12th international Conference on Intelligentuer Interfaces, ACM Press,2007:14-21.
[6] 李聪, 骆志刚, 石金龙. 一种探测推荐系统托篡改的无监督算法[J]. 自动化学报, 2013.39(10):1681-1690.DOI:10.3724/sp.J.1004.2013.01681. LI C, LUO Z G,SHI J L. Detecting shilling attacks in recommender systems based on Non-random-missing Mechanism [J].ACTA AUTOAMTICA SINICA, 2013.39(10):1681-1690.DOI:10.3724/sp.J..1004.2013.01681.
[7] 于洪涛,魏莎,张付志,等.基于多项目项目检索的无监督客户状态篡改识别算法[J].小型微型计算机系统,2013,34(9):2120-2124.DOI:10.3969/j.issn.1000-1220.2013.09.031. YU H T,WEI S, ZHANG F Z,et al. An unsupervised algorithm for detecting user profile attack based on multi-target items retrieval[J].Journal of Chinese Computer Systems, 2013,34(9):2120-2124.DOI:10.3969/j.issn.1000-1220.2013.09.031.
[8] TAN Z, JAMDAGNI A,HE X, et al. A system for denial-of-service attack detection based on multivariate correlation analysis[J].Parallel and Distributed Systems IEEE Transactions on, 2014,25(2):447-456.
[9] DACER M C, KARGL F, KONIGH,et al. Network attack detection and defense:securing industrial control systems for critical infrastructures(Dagstuhl Seminar 14292)[J]. Dagstuhl Report, 2014,4(7):62-79.
[10] 于洪涛, 李鹏, 张付志. 基于多维风险因子的推荐篡改识别方法[J].小型微型计算机系统,2015,36(5):971-975. YU H T, LI P, ZHANG F Z. Method for detecting recommendation attack based on multiple risk factors [J]. Journal of Chinese Computer Systems, 2015,36(5):971-975.
[11] 郝志峰, 牛晓龙, 蔡瑞初, 等.融合信息熵与信任机制的防篡改推荐算法研究[J].计算机应用与软件, 2015,32(3):284-288.DOI:3969/j.issn.1000-386x.2015.03.067. HAO Z F,NIU X L,CAI R C,et al.Research compiter applications and sortware anti-attack recommendation algorithm with fusion of information entropy and trust mechanism[J].Computer Application and Software,2015,32(3):284-288.DOI:3969/j.issn.1000-386x.2015.03.067.
[12] 岳猛, 吴志军, 姜军.云计算中基于可用带宽欧式距离的LDoS篡改识别方法[J].山东大学学报(理学版),2016,51(9):92-100.DOI:10.6040/j.issn.1671-9352.3.20.090. YUE M,WU Z J,JIANG J.An approach of detecting LDOS attacks based on the euclidean distance of available bandwidth in cloud computing[J].Journal of Shandong Universty(Natural Science),2016,51(9):92-100.DOI:10.6040/j.issn.1671-9352.3.20.090.
