With the prevalent adoption of blockchain in the financial system, there has been an increase in phishing scams on cryptocurrency platforms such as Ethereum, and an effective anomaly detection method is urgently requi...
详细信息
With the prevalent adoption of blockchain in the financial system, there has been an increase in phishing scams on cryptocurrency platforms such as Ethereum, and an effective anomaly detection method is urgently required. The latest studies have focused on anomaly identification using natural language processing techniques or constructing simple static graphs. However, the existing methods are insufficient to convey the diversity of connectivity patterns in the Ethereum transaction network concerning amount and time. To this end, we proposed a novel transaction network embedding algorithm transE based on the multi-channel random walk to model the detection of Ethereum phishing scam accounts as a multigraph node classification task. Specifically, we first model the Ethereum transaction as a time-amount directed multigraph. Then, the hybrid feature representation of network nodes is learned via transE from their local and global neighbours, which uses the attention mechanism to maximize the probability of preserving node network neighbours. Ultimately, we employ visualization techniques and machine learning models to validate the effectiveness of the algorithms, and the model with the top performance is picked for Ethereum account classification. Experimental results indicate that the embedding vector extracted by transE improves the detection accuracy of Ethereum phishing accounts in the different classification tasks.
暂无评论