Effective Illicit Account Detection on Large Cryptocurrency MultiGraphs

TL;DR

This paper introduces DIAM, a novel end-to-end method leveraging graph neural networks to effectively detect illicit accounts in large cryptocurrency transaction networks, significantly outperforming existing solutions.

Contribution

The paper presents DIAM, a new approach combining Edge2Seq and multigraph discrepancy modules for improved illicit account detection in complex cryptocurrency graphs.

Findings

DIAM achieves an F1 score of 96.55% on large Bitcoin datasets.

Outperforms 15 existing detection methods across multiple datasets.

Effectively captures transaction patterns and discrepancies in multi-graph structures.

Abstract

Cryptocurrencies are rapidly expanding and becoming vital in digital financial markets. However, the rise in cryptocurrency-related illicit activities has led to significant losses for users. To protect the security of these platforms, it is critical to identify illicit accounts effectively. Current detection methods mainly depend on feature engineering or are inadequate to leverage the complex information within cryptocurrency transaction networks, resulting in suboptimal performance. In this paper, we present DIAM, an effective method for detecting illicit accounts in cryptocurrency transaction networks modeled by directed multi-graphs with attributed edges. DIAM first features an Edge2Seq module that captures intrinsic transaction patterns from parallel edges by considering edge attributes and their directed sequences, to generate effective node representations. Then in DIAM, we design a multigraph Discrepancy (MGD) module with a tailored message passing mechanism to capture the discrepant features between normal and illicit nodes over the multigraph topology, assisted by an attention mechanism. DIAM integrates these techniques for end-to-end training to detect illicit accounts from legitimate ones. Extensive experiments, comparing against 15 existing solutions on 4 large cryptocurrency datasets of Bitcoin and Ethereum, demonstrate that DIAM consistently outperforms others in accurately identifying illicit accounts. For example, on a Bitcoin dataset with 20 million nodes and 203 million edges, DIAM attains an F1 score of 96.55%, markedly surpassing the runner-up's score of 83.92%. The code is available at https://github.com/TommyDzh/DIAM.