EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Abnormal Account Identification Method by Topology Feature Analysis for Blockchain-Based Transaction Network

Yuyu Yue, Jixin Zhang, Mingwu Zhang, Jia Yang

Electronics · 09.04.2024 · 13 (8) · 1416

DOI: 10.3390/electronics13081416 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 09.04.2024. Verfasst von Yuyu Yue und 3 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Major Research Plan of Hubei Province, National Natural Science foundation of China, The Natural Science Foundation of Hubei Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cryptocurrency, as one of the most successful applications of blockchain technology, has played a vital role in promoting the development of the digital economy. However, its anonymity, large scale of cryptographic transactions, and decentralization have also brought new challenges in identifying abnormal accounts and preventing abnormal transaction behaviors, such as money laundering, extortion, and market manipulation. Recently, some researchers have proposed efficient and accurate abnormal transaction detection based on machine learning. However, in reality, abnormal accounts and transactions are far less common than normal accounts and transactions, so it is difficult for the previous methods to detect abnormal accounts by training with such an imbalance in abnormal/normal accounts. To address the issues, in this paper, we propose a method for identifying abnormal accounts using topology analysis of cryptographic transactions. We consider the accounts and transactions in the blockchain as graph nodes and edges. Since the abnormal accounts may have special topology features, we extract topology features from the transaction graph. By analyzing the topology features of transactions, we discover that the high-dimensional sparse topology features can be compressed by using the singular value decomposition method for feature dimension reduction. Subsequently, we use the generative adversarial network to generate samples like abnormal accounts, which will be sent to the training dataset to produce an equilibrium of abnormal/normal accounts. Finally, we utilize several machine learning techniques to detect abnormal accounts in the blockchain. Our experimental results demonstrate that our method significantly improves the accuracy and recall rate for detecting abnormal accounts in blockchain compared with the state-of-the-art methods.

Förderung

  • The Major Research Plan of Hubei Province
  • National Natural Science foundation of China
  • The Natural Science Foundation of Hubei Province
  • The Research Foundation of Hubei University of Technology

Zitieren

APA

Yue, Y., Zhang, J., Zhang, M., & Yang, J. (2024). An Abnormal Account Identification Method by Topology Feature Analysis for Blockchain-Based Transaction Network. Electronics, 13(8), 1416. https://doi.org/10.3390/electronics13081416

Vancouver

Yue Y, Zhang J, Zhang M, Yang J. An Abnormal Account Identification Method by Topology Feature Analysis for Blockchain-Based Transaction Network. Electronics. 2024;13(8):1416. doi:10.3390/electronics13081416

BibTeX
@article{Yue2024,
  author = {Yue, Yuyu and Zhang, Jixin and Zhang, Mingwu and Yang, Jia},
  title = {An Abnormal Account Identification Method by Topology Feature Analysis for Blockchain-Based Transaction Network},
  journal = {Electronics},
  year = {2024},
  volume = {13},
  number = {8},
  pages = {1416},
  doi = {10.3390/electronics13081416}
}
Kostenlos starten →