Unveiling Blockchain Transactions Insights: Behavioral Anomaly Detection via Relational Mechanisms

Blockchain technology has evolved from its initial use in decentralized payments to encompass smart contracts and applications across multiple domains, propelling the digital transformation of various industries. However, the decentralized and anonymous nature of blockchain presents challenges for anomaly detection, increasing the complexity of security management. The core issue lies in how to efficiently process massive amounts of data and accurately identify anomalous transactions. To address these challenges, this paper proposes an innovative method called BAD-CLRM, which aims to leverage a large amount of unlabeled data in the blockchain and the relationships between the features of various transaction nodes. We explore the feature distribution of temporal transaction nodes and infer the label attributes of node clusters through contrastive learning, thereby maximizing model learning efficiency and reducing manual labeling costs. Consequently, we leverage the relational mechanism to construct behavioral and structural feature information of nodes during transactions, providing comprehensive understanding and support for node anomaly detection. Experimental results demonstrate that our model exhibits flexibility, superiority, and efficiency in anomaly detection tasks, outperforming existing models, especially in handling dynamic transaction data and unlabeled data.