Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 16, 2025Journal of Organizational and End User ComputingOpen Access

Neighborhood Subgraph-Based Illicit Transaction Detection in Cryptocurrency Networks

View Full Paper
Ask AI
Bookmark
Share

Authors

SJShenghao JinHZHui ZhangQYQiwen Yang

Discussion

Loading...

Member takes

Overview

Novel neighborhood subgraph method improves illicit transaction detection in cryptocurrency networks, indicating enhanced efficacy.

Key Points

  • This method significantly outperforms baseline models in detecting illicit transactions in cryptocurrency networks.
  • Using 3-hop neighborhood subgraphs, the approach utilizes data from only an average of 80 nodes.
  • The GCN captures local network structure information, while the LSTM tracks fund flow variations.
  • This technique enhances efficiency over traditional methods relying on entire transaction networks.

Cite This Study

Jin et al. (2025) studied this question.

synapsesocial.com/papers/68d453a431b076d99fa599b8https://doi.org/10.4018/joeuc.388738
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Enhancing Illegal Activities in Crypto Currency Using Graph Neural Networks2026
  2. 2Exploring the Use of Graph Neural Networks for Blockchain Transaction Analysis and Fraud Detection2024 · 1 citations
  3. 3Illicit Bitcoin transaction detection via feature-gated temporal graph learning2026
  4. 4Blockchain Fraud Detection Using Ensemble Graph Neural Networks2025
  5. 5Detection of anomalous cryptocurrency transactions using neural networks and ontologies2025