计算机科学 ›› 2023, Vol. 50 ›› Issue (8): 260-270.doi: 10.11896/jsjkx.221000103
李洋1, 李振华1, 辛显龙2
LI Yang1, LI Zhenhua1, XIN Xianlong2
摘要： 受电信资源充分利用和激发良性市场竞争的双重驱动,移动虚拟运营商(虚商)近年来迅速流行,其依靠基础运营商的基础设施为用户提供更灵活优惠的服务。考虑到线下实体店维护成本较高,虚商基本上采取完全线上的服务方式,这给用户监管带来很大困难;很多不法分子利用在线身份认证漏洞,大量购买虚商电话卡拨打诈骗电话,严重损害了虚商及其用户声誉,成为目前虚商存续发展的瓶颈。为解决该难题,与拥有超两百万用户的主流虚商“小米移动”合作研究,发现相关工作普遍假设诈骗电话是随意的、零散的或隐蔽的,导致其检测方法对于虚商场景低效甚至无效。然而,通过人工分析发现,不同于传统假设,虚商场景中几乎所有的诈骗电话都是有组织、按计划、成规模的,从而提出基于攻击经济学、合理分析诈骗电话时空特征的新型检测方法,成功提取出有效甄别的关键特征,再结合机器学习分类,将诈骗用户的比例降低至0.023‰,远低于基础运营商在信息充分的前提下所达到的0.1‰。在避免所提方案被破解的前提下,已将部分代码和数据开源,以帮助净化整个产业生态。
中图分类号:
| [1]DAHLMAN E,MILDH G,PARKVALL S,et al.5G evolution and beyond[J].IEICE Transactions on Communications,2021,104(9):984-991. [2]CHAN P P K,LIU W,CHEN D,et al.Face liveness detectionusing a flash against 2D spoofing attack[J].IEEE Transactions on Information Forensics and Security,2017,13(2):521-534. [3]PAN G,SUN L,WU Z,et al.Monocular camera-based face liveness detection by combining eyeblink and scene context[J].Tele-communication Systems,2011,47(3):215-225. [4]DALE K,SUNKAVALLI K,JOHNSON M K,et al.Video face replacement[C]//Proceedings of the ACM Special Interest Group on Computer Graphics and Interactive Techniques(SIG-GRAPH).2011:1-10. [5]XIAO A,LIU Y,LI Y,et al.An in-depth study of commercial MVNO:Measurement and optimization[C]//Proceedings of the 17th Annual International Conference on Mobile Systems,Applications,and Services(MobiSys).2019:457-468. [6]LI Y,ZHENG J,LI Z,et al.Understanding the ecosystem and addressing the fundamental concerns of commercial MVNO[J].IEEE/ACM Transactions on Networking,2020,28(3):1364-1377. [7]GOPAL R K,MEHER S K.A rule-based approach for anomaly detection in subscriber usage pattern[C]//Proceedings of the World Academy Science,Engineering Technology(WASET).2007:396-399. [8]ZHOU C,LIN Z.Study on fraud detection of telecom industry based on rough set[C]//Proceedings of the Annual Computing and Communication Workshop and Conference(CCWC).IEEE,2018:15-19. [9]NORTHCUTT C,JIANG L,CHUANG I.Confident learning:estimating uncertainty in dataset labels[J].Journal of Artificial Intelligence Research,2021,70(1):1373-1411. [10]WANG Z,WU C,ZHENG K,et al.SMOTETomek-based resam-pling for personality recognition[J].IEEE Access,2019,7(1):129678-129689. [11]DEVI D,BISWAS S K,PURKAVASTHA B,et al.Redundancy-driven modified Tomek-link based undersampling:a solution to class imba-lance[J].Pattern Recognition Letters,2017,93(C):3-12. [12]HAN H,WANG W Y,MAO B H.Borderline-SMOTE:a newover-sampling method in imbalanced data sets learning[C]//Proceedings of the International Conference on Intelligent Computing(ICIC).Springer,2005:878-887. [13]SUBUDHI S,PANIGRAHI S.Use of possibilistic fuzzy c-means clustering for telecom fraud detection[C]//Proceedings of the International Conference on Computational Intelligence in Data Mining(CIDM).Springer,2017,10:633-641. [14]LI R,ZHANG Y,TUO Y,et al.A novel method for detecting telecom fraud user[C]//Proceedings of the International Conference on Information Systems Engineering(ICISE).IEEE,2018:46-50. [15]CHOUIEKH A,HAJ E H I E.Convnets for fraud detectionanalysis[J].Procedia Computer Science,2018,127(C):133-138. [16]LIU X,WANG X G.Probabilistic graphical model based ap-proach for bank telecommunication fraud detection[J].Compu-ter Science,2018,45(7):122-128. [17]LU C,LIN S,LIU X,et al.Telecom fraud identification based on ADASYN and random forest[C]//Proceedings of the International Conference on Computer and Communication Systems(ICCCS).IEEE,2020:447-452. [18]NI P,YU W.A victim-based framework for telecom fraud ana-lysis:a Bayesian network model[J].Computational Intelligence and Neuroscience,2022,2022:1-13. [19]HU X,CHEN H,LIU S,et al.BTG:a bridge to graph machine learning in telecommunications fraud detection[J].Future Ge-neration Computer Systems,2022,137:274-287. [20]XU H K,JIANG T T,LI X,et al.BiLSTM network fraud phone recognition based on attention mechanism[J].Computer Systems and Applications,2022,31(3):326-332. [21]KARUNATHILAKA A.Fraud detection on international direct dial calls[M]//Diss.2021. [22]KASHIR M,BASHIR S.Machine learning techniques for sim box fraud detection[C]//Proceedings of the International Conference on Communication Technologies(ComTech).IEEE,2019:4-8. [23]ZHOU G M,CHEN G X,ZHOU Y Z.Research on telecomfraud user behavior based on CDR analysis[J].Information Security and Communication Privacy,2015,11(1):114-118. [24]LI Y,LIN H,LI Z,et al.A nationwide study on cellular reliability:measurement,analysis,and enhancements[C]//Proceedings of the 2021 ACM SIGCOMM 2021 Conference.2021:597-609. [25]MIN X,LIN R.K-means algorithm:fraud detection based on signaling data[C]//Proceedings of the IEEE World Congress on Services.IEEE,2018:21-22. [26]LIU M,LIAO J,WANG J,et al.AGRM:attention-based graph representation model for telecom fraud detection[C]//Procee-dings of the International Conference of Communications(ICC).IEEE,2019:1-6. [27]TERZI D S,SAGIROGLU Ş,KILINC H.Telecom fraud detection with big data analytics[J].International Journal of DataScience,2021,6(3):191-204. [28]CHADYSAS V,BUGAJEV A,KRIAUZIENE R,et al.Outlier analysis for telecom fraud detection[C]//Proceedings of the International Baltic Conference on Digital Business and Intelligent Systems(CCIS).Cham:Springer,2022:219-231. [29]JIANG Y,LIU G,WU J,et al.Telecom fraud detection viaHawkes-enhanced sequence model[J].IEEE Transactions on Knowledge and Data Engineering,2022,35(5):5311-5324. [30]KRASIC I,ČELAR S.Telecom fraud detection with machinelearning on imbalanced dataset[C]//Proceedings of 2022 International Conference on Software,Telecommunications and Computer Networks(SoftCOM).IEEE,2022:1-6. [31]ZHANG J J,TANG Y C,JI S Y.A telecom fraud identification method based on graph neural network[J].Application of Electronic Technique,2021,47(6):25-29. [32]YANG J K,XIA W C.Fraud call identification based on user be-havior analysis[J].Computer Systems and Applications,2021,30(8):311-316. [33]LIU G,GUO J,ZUO Y,et al.Fraud detection via behavioral sequence embedding[J].Knowledge and Information Systems,2020,62(7):2685-2708. [34]FAN Y R,YANG T,KONG H F,et al.Calling features mining method of telecom fraud based on knowledge graph[J].Compu-ter Applications and Software,2019,36(11):182-187. [35]CAMERON A C,WINDMEIJER F A G.An R-squared measure of goodness of fit for some common nonlinear regression models[J].Journal of Econometrics,1997,77(2):329-342. [36]ZAR J H.Spearman rank correlation[M]//Encyclopedia of Biostatistics.2005. [37]HE H,GARCIA E A.Learning from imbalanced data[J].IEEE Transactions on Knowledge and Data Engineering,2009,21(9):1263-1284. [38]SUYKENS J A K,VANDEWALLE J.Least squares support vector machine classifiers[J].Neural Processing Letters,1999,9(3):293-300. [39]GARDNER M W,DORLING S R.Artificial neural networks(the multilayer perceptron)—a review of applications in the atmospheric sciences[J].Atmospheric Environment,1998,32(14/15):2627-2636. [40]FRIEDMAN J H.Greedy function approximation:a gradient boosting machine[J].Annals of Statistics,2001,29(1):1189-1232. [41]HIDO S,KASHIMA H,TAKAHASHI Y.Roughly balanced bagging for imbalanced data[J].Statistical Analysis and Data Mining:The ASA Data Science Journal,2009,2(5/6):412-426. [42]AGUSTA Z P.Modified balanced random forest for improving imbalanced data prediction[J].International Journal of Advances in Intelligent Informatics,2019,5(1):58-65. [43]NEMBRINI S,KONIG I R,WRIGHT M N.The revival of the Gini importance[J].Bioinformatics,2018,34(21):3711-3718. [44]DONG X,QIAN M,JIANG R.Packet classification based on the decision tree with information entropy[J].The Journal of Supercomputing,2020,76(6):4117-4131. [45]ZHANG Z,PU P,HAN D,et al.Self-adaptive louvain algorithm:fast and stable community detection algorithm based on the principle of small probability event[J].Physica A:Statistical Mechanics and its Applications,2018,506(1):975-986. |
|
||
首页