Know Your Account: Double Graph Inference-based Account De-anonymization on Ethereum

TL;DR

This paper introduces DBG4ETH, a double graph inference method that enhances Ethereum account de-anonymization by analyzing static and dynamic transaction graphs, significantly improving identification accuracy over existing methods.

Contribution

The paper presents a novel double graph-based approach combining static and dynamic graphs with adaptive confidence calibration for improved Ethereum account de-anonymization.

Findings

Achieves state-of-the-art F1-score improvements of up to 40.52%.

Outperforms existing methods by 5.23% to 12.91%.

Effectively captures behavioral patterns through combined static and dynamic graph analysis.

Abstract

The scaled Web 3.0 digital economy, represented by decentralized finance (DeFi), has sparked increasing interest in the past few years, which usually relies on blockchain for token transfer and diverse transaction logic. However, illegal behaviors, such as financial fraud, hacker attacks, and money laundering, are rampant in the blockchain ecosystem and seriously threaten its integrity and security. In this paper, we propose a novel double graph-based Ethereum account de-anonymization inference method, dubbed DBG4ETH, which aims to capture the behavioral patterns of accounts comprehensively and has more robust analytical and judgment capabilities for current complex and continuously generated transaction behaviors. Specifically, we first construct a global static graph to build complex interactions between the various account nodes for all transaction data. Then, we also construct a local dynamic graph to learn about the gradual evolution of transactions over different periods. Different graphs focus on information from different perspectives, and features of global and local, static and dynamic transaction graphs are available through DBG4ETH. In addition, we propose an adaptive confidence calibration method to predict the results by feeding the calibrated weighted prediction values into the classifier. Experimental results show that DBG4ETH achieves state-of-the-art results in the account identification task, improving the F1-score by at least 3.75% and up to 40.52% compared to processing each graph type individually and outperforming similar account identity inference methods by 5.23% to 12.91%.