基于图注意力Transformer神经网络的信用卡欺诈检测模型  

Credit card fraud detection model based on graph attention Transformation neural network

作　　者：杨帆[1] 邹窈 朱明志 马振伟 程大伟 蒋昌俊[2,3] YANG Fan;ZOU Yao;ZHU Mingzhi;MA Zhenwei;CHENG Dawei;JIANG Changjun(China UnionPay,Shanghai 200135,China;Department of Computer Science and Technology,Tongji University,Shanghai 201804,China;Collaborative Innovation Center for Internet Financial Security,Tongji University,Shanghai 201804,China)

机构地区：[1]中国银联,上海200135 [2]同济大学计算机科学与技术系,上海201804 [3]同济大学网络金融安全国家级协同创新中心,上海201804

出　　处：《计算机应用》2024年第8期2634-2642,共9页journal of Computer Applications

基　　金：国家自然科学基金资助项目(62102287);上海市科技创新行动计划项目(22511100700,22YS1400600)。

摘　　要：针对现有模型无法精准识别复杂多变的团伙诈骗模式的问题,提出一种新型实用的基于复杂交易图谱的信用卡反欺诈检测模型。首先,利用用户原始的交易信息构造关联交易图谱;随后,使用图自注意力Transformer神经网络模块直接从交易网络中挖掘团伙欺诈特征,无需构建繁冗的特征工程;最后,通过欺诈预测网络联合优化图谱中的拓扑模式和时序交易模式,实现对欺诈交易的高精度检测。在信用卡交易数据上的反欺诈实验结果表明,所提模型在全部评价指标上均优于7个对比的基线模型:在交易欺诈检测任务中,平均精度(AP)比基准图注意力神经网络(GAT)提升了20%,ROC曲线下方面积(AUC)平均提升了2.7%,验证了所提模型在信用卡欺诈交易检测中的有效性。For the issue of existing models’inability to accurately identify intricate and diverse patterns of gang fraud,a new practical credit card fraud detection model based on complex transaction graph was proposed.Firstly,the association transaction graph was constructed based on the original transaction information of the users,then the graph Transformer neural network module was employed to mine the gang fraud characteristics directly from the transaction network without cumbersome feature engineering.Finally,the high-precision detection of fraud transactions was realized by jointly optimizing the topological features and sequential transaction features by the fraud detection network.The credit card antifraud experiment results showed that the proposed model outperformed seven benchmark models in all evaluation indexes.The Average-Precision(AP)improved by 20%and the Area Under the ROC Curve(AUC)increased by an average of 2.7%over the best benchmark Graph Attention Network(GAT)model in transaction fraud detection tasks.These results indicate that the proposed model is effective in the detection of credit card fraud transactions.

关 键 词：信用卡交易 欺诈检测 图神经网络 自注意力Transformer 异构图 

分 类 号：TP389.1[自动化与计算机技术—计算机系统结构]