Blockchain is gradually becoming an important data storage platform for Internet digital copyright confirmation, electronic deposit, and data sharing. Anomaly detection on the blockchain has received extensive attention as the foundation for securing blockchain-based digital applications. However, the current blockchain anomaly detection for obtaining network nodes’ depth and dynamic change features still needs improvement. In this paper, we propose a public blockchain anomaly detection method based on evolved graph attention. Different from general blockchain network modeling methods, we first adopt a dynamic attribute graph network construction method to model each transaction using edges to provide more learnable transaction attribute information for graph representation learning in blockchain networks. Then, we propose an evoluted graph attention network structure to fully extract the deep features of blockchain nodes by learning the temporal evolution characteristics of blockchain networks and dynamically updating the node learning weights of subgraphs in different timestamps. In order to solve the dataset imbalance problem, we also apply the GraphSMOTE method for graph-structured data on public blockchain networks for the first time. Finally, we identify node labels in blockchain networks using a binary classification method and verify our proposed scheme through multiple rounds of experiments.

区块链正逐渐成为互联网数字版权确权、电子存证、数据共享的重要数据存储平台。区块链上的异常检测作为保护基于区块链的数字应用程序的基础而受到广泛关注。然而，目前区块链异常检测获取网络节点的深度和动态变化特征仍然需要改进。在本文中，我们提出了一种基于演化图注意力的公共区块链异常检测方法。与一般的区块链网络建模方法不同，我们首先采用动态属性图网络构建方法，利用边对每笔交易进行建模，为区块链网络中的图表示学习提供更多可学习的交易属性信息。然后，我们提出了一种进化图注意力网络结构，通过学习区块链网络的时间演化特征并动态更新不同时间戳下子图的节点学习权重来充分提取区块链节点的深层特征。为了解决数据集不平衡问题，我们还首次将GraphSMOTE方法应用于公共区块链网络上的图结构数据。最后，我们使用二元分类方法识别区块链网络中的节点标签，并通过多轮实验验证我们提出的方案。