Tracing Your Account: A Gradient-Aware Dynamic Window Graph Framework for Ethereum under Privacy-Preserving Services

TL;DR

This paper introduces GradWATCH, a novel framework that leverages gradient-aware dynamic window graphs to effectively de-anonymize accounts in Ethereum's privacy-preserving services, addressing challenges of transaction similarity, temporal gaps, and graph sparsity.

Contribution

The paper presents a new gradient-aware dynamic window graph framework with a learnable feature mapping and edge-aware sliding window to improve account de-anonymization in Ethereum.

Findings

Achieves 1.62% to 15.22% improvement in MRR

Achieves 3.85% to 7.31% improvement in F1 score

Effective under unbalanced labels and sparse transactions

Abstract

With the rapid advancement of Web 3.0 technologies, public blockchain platforms are witnessing the emergence of novel services designed to enhance user privacy and anonymity. However, the powerful untraceability features inherent in these services inadvertently make them attractive tools for criminals seeking to launder illicit funds. Notably, existing de-anonymization methods face three major challenges when dealing with such transactions: highly homogenized transactional semantics, limited ability to model temporal discontinuities, and insufficient consideration of structural sparsity in account association graphs. To address these, we propose GradWATCH, designed to track anonymous accounts in Ethereum privacy-preserving services. Specifically, we first design a learnable account feature mapping module to extract informative transactional semantics from raw on-chain data. We then incorporate transaction relations into the account association graph to alleviate the adverse effects of structural sparsity. To capture temporal evolution, we further propose an edge-aware sliding-window mechanism that propagates and updates gradients at three granularities. Finally, we identify accounts controlled by the same entity by measuring their embedding distances in the learned representation space. Experimental results show that even under the conditions of unbalanced labels and sparse transactions, GradWATCH still achieves significant performance gains, with relative improvements ranging from 1.62% to 15. 22% in the MRR and from 3. 85% to 7. 31% in the F_1.