基于强化图卷积和时空循环门的区块链非法交易检测方法  

Blockchain fraud detection method based on reinforced graph convolutional network and spatiotemporal recurrent gates

作　　者：夏鑫 任秀丽[1] Xia Xin;Ren Xiuli(College of Information,Liaoning University,Shenyang 110036,China)

机构地区：[1]辽宁大学信息学院,沈阳110036

出　　处：《计算机应用研究》2024年第9期2592-2597,共6页Application Research of Computers

基　　金：辽宁省教育厅资助项目(LYB201617);国家重点研发计划资助项目(2019YFB1406002);国家自然科学基金资助项目(61871107);辽宁省自然科学基金资助项目(201202089)。

摘　　要：区块链非法交易检测任务需要充分挖掘历史交易数据中固有的时间和空间特征。针对现有的非法交易检测方法存在误差较大的问题,提出一种基于强化图卷积和时空循环门的区块链非法交易检测方法(RGCN-SRG)。首先,利用比特币区块链历史交易数据构造交易图谱,引入一组具有不同尺寸卷积核的强化图卷积网络(RGCN),全面地提取该图谱的拓扑信息并生成特征向量;另外,考虑到区块链交易的时序特点,提出一种时空循环门结构(SRG),在传统门结构中引入图卷积运算,以提取交易图多个时空维度的依赖信息;最后,经过一个线性层和激活函数输出非法交易检测的预测结果。将提出的方法与GCN、DEDGAT、EGT以及GCN+MLP进行比较,在F 1方面,分别提高了18.4、10.7、9.3和4.9百分点;在精度方面,分别提高了11.5、11.2、7.7和3.7百分点。The task of fraud detection in blockchain requires a thorough exploration of the inherent temporal and spatial cha-racteristics in historical transaction data.Existing fraud detection methods suffer from large prediction errors.To address this issue,this paper proposed a blockchain fraud detection method,named RGCN-SRG,based on reinforced graph convolutional network(RGCN)and spatiotemporal recurrent gate(SRG).Firstly,leveraging Bitcoin’s historical transaction data for the construction of the transaction graph,the method used a reinforced graph convolutional network with different kernel sizes to comprehensively extract the graph’s topology information and generate feature vectors.Additionally,considering the temporal characteristics of blockchain transactions,the method introduced a spatiotemporal recurrent gate structure that incorporated graph convolutional operations into the traditional gate structure to extract dependency information from multiple spatiotemporal dimensions of the transaction graph.Finally,it obtained the prediction results of money laundering detection through a linear layer and activation function.The proposed fraud detection method was evaluated by the constructed dataset.Compared with GCN,DEDGAT,EGT and GCN+MLP F 1 by the proposed method improves 18.4,10.7,9.2 and 4.9 percentage points,respectively;the precision improves 11.5,11.2,7.7 and 3.7 percentage points,respectively.

关 键 词：区块链 比特币网络 图卷积网络 非法交易识别 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]