Visual Analysis of Money Laundering in Cryptocurrency Exchange

Zhou, Fangfang; Chen, Yunpeng; Zhu, Chunyao; Jiang, Lijia; Liao, Xincheng; Zhong, Zengsheng; Chen, Xiaohui; Chen, Yi; Zhao, Ying

doi:10.1109/tcss.2022.3231687

Cited by 5 publications

(2 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, the process of money laundering involves complicated financial activities that may exhibit distinctions from normal ones, such as large-block or high-frequency transactions, the reactivation of dormant addresses, and the immediate closures of newly opened addresses [ 35 ]. Zhou et al [ 36 ] defined a feature system consisting of 40 statistical features to characterize a money laundering transaction behavior based on that domain knowledge. However, most rule-based algorithms are based on empirical inferences and may become ineffective when facing rule changes.…”

Section: Related Workmentioning

confidence: 99%

Bitcoin Money Laundering Detection via Subgraph Contrastive Learning

Ouyang,

Bai,

Feng

et al. 2024

Entropy

View full text Add to dashboard Cite

The rapid development of cryptocurrencies has led to an increasing severity of money laundering activities. In recent years, leveraging graph neural networks for cryptocurrency fraud detection has yielded promising results. However, many existing methods predominantly focus on node classification, i.e., detecting individual illicit transactions, rather than uncovering behavioral pattern differences among money laundering groups. In this paper, we tackle the challenges presented by the organized, heterogeneous, and noisy nature of Bitcoin money laundering. We propose a novel subgraph-based contrastive learning algorithm for heterogeneous graphs, named Bit-CHetG, to perform money laundering group detection. Specifically, we employ predefined metapaths to construct the homogeneous subgraphs of wallet addresses and transaction records from the address–transaction heterogeneous graph, enhancing our ability to capture heterogeneity. Subsequently, we utilize graph neural networks to separately extract the topological embedding representations of transaction subgraphs and associated address representations of transaction nodes. Lastly, supervised contrastive learning is introduced to reduce the effect of noise, which pulls together the transaction subgraphs with the same class while pushing apart the subgraphs with different classes. By conducting experiments on two real-world datasets with homogeneous and heterogeneous graphs, the Micro F1 Score of our proposed Bit-CHetG is improved by at least 5% compared to others.

show abstract

Section: Related Workmentioning

confidence: 99%

Bitcoin Money Laundering Detection via Subgraph Contrastive Learning

Ouyang,

Bai,

Feng

et al. 2024

Entropy

View full text Add to dashboard Cite

show abstract

“…These visual elements connect all network nodes and provide flexibility to monitor and compare the large volume of transactions on the same page in different time frames. These facilities support human experts in decisionmaking within their domains, including forensic analysts [4], network administrators, investors, and researchers. Well informed decisions will ensure a secure and legitimate transfer of digital assets in blockchain networks.…”

Section: Introductionmentioning

confidence: 99%

Visualizing Blockchain Transaction Behavioural Pattern: A Graph-based Approach

Jeyakumar¹,

Hóu²,

Yugarajah³

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>This paper proposes a novel graph-based visualisation approach to incorporating automated graph modelling and generalised graph algorithms from blockchain transactions. Our approach enables users to interact directly with the blockchain data using graph queries and provides exploration capabilities through graph patterns. Four case studies are presented, demonstrating the benefits of the proposed approach in identifying the behaviour of anomalous nodes. The visual assessment of behavioural patterns informs the challenges in classifying anomalous nodes. The proposed approach also has the potential to be used in other types of networks for inferring and verifying heuristics.</p>

show abstract