Improving Ethereum Mixing Address Linking With Tensor Computation, Neighbor Data Utilization, and Asymmetric Information Modeling
- 13 August 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 20 (15566013) , 8658-8671
Abstract
Due to the strong untraceability of mixing services, numerous criminals exploit these services to engage in illicit activities, posing a significant threat to the blockchain ecosystem. This paper addresses the challenge of linking transaction addresses in Tornado Cash, a popular mixing service on Ethereum. While existing state-of-the-art solutions like MixBroker attempt to address this problem, two fundamental limitations persist: insufficient utilization of neighbor information and neglect of address information asymmetry. To address these gaps, a novel framework termed “MixLinker” is proposed, which enhances neighbor information utilization and models information asymmetry. Specifically, a Normalized Adjusted Personal PageRank (NAPPR) module is designed to prioritize significant neighbor nodes while mitigating interference from super and irrelevant addresses. Additionally, tensors are employed to model transactions, capturing rich interaction features related to transaction attributes. Based on historical transaction sequences, Tensor Long Short-Term Memory (TLSTM) is used to obtain high-quality initial input features for the Graph Neural Network (GNN) module, enabling effective learning of nonlinear dynamics. To ensure symmetric output results and model asymmetric information, a temporal-aware symmetry classifier is constructed that leverages asymmetric information through permutation operations and an order-aware classifier. Extensive experiments demonstrate that MixLinker outperforms other methods, validating the effectiveness of the proposed approach and confirming the two underlying motivations.Keywords
Funding Information
- National Natural Science Foundation of China (U23A20300)
- National Key Research and Development Program of China (2022YFE0138600)
- National Natural Science Foundation of China (U24B20153, 62272182)
- Fundamental Research Funds for the Central Universities, HUST (2025JYCXJJ036, 2024JYCXJJ056)
- Shenzhen Science and Technology Program (JCYJ20220530161004009)
This publication has 31 references indexed in Scilit:
- Fingerprinting Bitcoin entities using money flow representation learningApplied Network Science, 2023
- Abnormal Transactions Detection in the Ethereum Network Using Semi-Supervised Generative Adversarial NetworksIEEE Access, 2023
- Mixing detection on Bitcoin transactions using statistical patternsIET Blockchain, 2023
- Mixers Detection in bitcoin network: a step towards detecting money laundering in crypto-currencies2022
- Analysis of Address Linkability in Tornado Cash on Ethereum2022
- Blockchain is Watching You: Profiling and Deanonymizing Ethereum Users2021
- XBlock-ETH: Extracting and Exploring Blockchain Data From EthereumIEEE Open Journal of the Computer Society, 2020
- Wiley Series in Probability and Statistics2008
- Local Graph Partitioning using PageRank Vectors2006
- Random ForestsMachine Learning, 2001