Skip to content
All library documents

Real-CATS: A Labeled Dataset for Cryptocurrency Cybercrime Detection

Article arXiv papers · Author: Jiadong Shi et al.
Read the original

Summary

The document introduces Real-CATS, a dataset intended to support the development and evaluation of cryptocurrency address detection methods. It combines addresses identified as criminal in real-world reports with benign addresses associated with exchange customers, providing labeled examples for research where accessible real-world data has been scarce.

The authors describe three uses: comparing detection methods, extending the dataset with additional features, and evaluating methods in a setting intended to reflect real-world deployment. They frame dataset quality around comprehensiveness, classifiability, customizability, and transferability. The summary gives dataset sizes and provenance, but no detection benchmarks or evidence that a particular method performs well. Results may depend on how the labels were collected and how closely the sample represents addresses encountered in deployment, so the dataset is a research resource rather than proof of operational accuracy.

Key ideas

  • Real-world labeled addresses can help address data scarcity in cryptocurrency cybercrime research.
  • The dataset pairs reported criminal addresses with benign addresses from exchange customers.
  • It is intended for method evaluation, feature extension, and deployment-oriented assessment.
  • The document describes dataset scope but reports no comparative detection performance.

Tags

CryptoMachine learningOn-chain dataStatistics
Full text
# Real-CATS: A Practical Training Ground for Emerging Research on Cryptocurrency Cybercrime Detection


# Real-CATS: A Practical Training Ground for Emerging Research on Cryptocurrency Cybercrime Detection









Cybercriminals pose a significant threat to blockchain trading security, causing $40.9 billion in losses in 2024. However, the lack of an effective real-world address dataset hinders the advancement of cybercrime detection research. The anti-cybercrime efforts of researchers from broader fields, such as statistics and artificial intelligence, are blocked by data scarcity. In this paper, we present Real-CATS, a Real-world dataset of Cryptocurrency Addresses with Transaction profileS, serving as a practical training ground for developing and assessing detection methods. Real-CATS comprises 103,203 criminal addresses from real-world reports and 106,196 benign addresses from exchange customers. It satifies the C3R characteristics (Comprehensiveness, Classifiability, Customizability, and Real-world Transferability), which are fundemental for practical detection of cryptocurrency cybercrime. The dataset provides three main functions: 1) effective evaluation of detection methods, 2) support for feature extensions, and 3) a new evaluation scenario for real-world deployment. Real-CATS also offers opportunities to expand cybercrime measurement studies. It is particularly beneficial for researchers without cryptocurrency-related knowledge to engage in this emerging research field. We hope that studies on cryptocurrency cybercrime detection will be promoted by an increasing number of cross-disciplinary researchers drawn to this versatile data platform. All datasets are available at https://github.com/sjdseu/Real-CATS

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.