Anomaly Detection in Blockchain Using Multi-source Embedding and Attention Mechanism

Due to the lack of effective regulatory mechanisms, many risks and offences have emerged in the blockchain trading market. Therefore, in order to achieve anomaly detection for blockchain networks, this paper abstracts blockchain transaction data as a graph structure and proposes GraphAEAtt, a deep learning model based on multi-source embedding and attention mechanism. GraphAEAtt uses two encoders to generate structure embeddings and feature embeddings respectively, and utilizes attention mechanisms to generate composite embeddings. By using multiple embeddings and attention mechanisms, the GraphAEAtt model can integrate the structural information and feature information of the graph, while also learning the relationships between nodes to reduce the impact of abnormal nodes on the learning process. Experimental results on several datasets show that the deep learning model proposed in this paper can better explore the implicit information in blockchain transaction graphs compared to other methods, thereby more accurately identifying abnormal transactions on the blockchain.