Machine Learning Algorithms to Detect Illicit Accounts on Ethereum Blockchain - A Published Conference Paper

Aug 4, 2026

Upload by Noah

Blockchain’s rapid growth and pseudonymity—intended to reduce reliance on centralized intermediaries—also enables illicit behavior such as fraud, phishing, scams, and the creation of illicit accounts. This work addresses the problem by investigating and implementing six machine learning algorithms with a focus on balancing accuracy, precision, and recall. It applies a synthetic minority over-sampling technique to handle data imbalance, improving performance. The light gradient boosting machine classifier reaches 98.4%, supporting stronger security and credibility for blockchain ecosystems.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages7

Reading Time18 min

AccessFree to download

Abstract

Keywords

1 Introduction

Please cite the Published Version Obi-Okoli, Chibuzo , Jogunola, Olamide , Adebisi, Bamidele and Hammoudeh, Mohammad (2023) Machine Learning Algorithms to Detect Illicit Accounts on Ethereum Blockchain. In: ICFNDS '23: The International Conference on Future Networks and Distributed Systems, 21 December 2023-22 December 2023, Dubai, United Arab Emirates. DOI: [https://doi.org/10.1145/3644713.3644838](https://doi.org/10.1145/3644713.3644838) Publisher: Association for Computing Machinery (ACM) Version: Published Version Downloaded from: [https://e-space.mmu.ac.uk/636228/](https://e-space.mmu.ac.uk/636228/) Usage rights: Creative Commons: Attribution 4 .0 Additional Information: This is an open access conference paper of a presentation ﬁrst given at ICFNDS '23: The International Conference on Future Networks and Distributed Systems Enquiries: If you have questions about this document, contact [openresearch@mmu.ac.uk. Please](openresearch@mmu.ac.uk. Please) include the URL of the record in e-space. If you believe that your, or a third party's rights have been compromised through this document please see our Take Down policy (available from [https://www.mmu.ac.uk/library/using-the-library/policies-and-guidelines](https://www.mmu.ac.uk/library/using-the-library/policies-and-guidelines)) Machine Learning Algorithms to Detect Illicit Accounts on Ethereum Blockchain Chibuzo Obi-Okoli [chibuzo.d.obi-okoli@stu.mmu.ac.uk](chibuzo.d.obi-okoli@stu.mmu.ac.uk)[ ](chibuzo.d.obi-okoli@stu.mmu.ac.uk)Manchester Metropolitan University Manchester, UK Olamide Jogunola∗ [o.jogunola@mmu.ac.uk](o.jogunola@mmu.ac.uk)[ ](o.jogunola@mmu.ac.uk)Manchester Metropolitan University Manchester, UK Bamidele Adebisi [b.adebisi@mmu.ac.uk](b.adebisi@mmu.ac.uk)[ ](b.adebisi@mmu.ac.uk)Manchester Metropolitan University Manchester, UK Mohammad Hammoudeh [mohammad.hammoudeh@kfupm.edu.sa](mohammad.hammoudeh@kfupm.edu.sa)[ ](mohammad.hammoudeh@kfupm.edu.sa)King Fahd University of Petroleum and Minerals Dhahran, Saudi Arabia ABSTRACT The rapid growth and psudonomity inherent in blockchain technology such as in Bitcoin and Ethereum has marred its original intent to reduce dependant on centralised system, but created an avenue for illicit activities, including fraud, phishing, scams, etc. This undermines the reputation of blockchain network, giving rise to the need to identify these illicit activities within the blockchain network. This current work tackles this crucial problem by investigating and implementing six machine learning algorithms with a particular emphasis on striking a balance between accuracy, precision and recall. The novelty of the work lies in the utilising of the synthetic minority over-sampling technique to handle data imbalance. Thus, increasing the accuracy of the light gradient boosting machine classifier to 98.4% . The outcome of this work holds great potential for enhancing the security and credibility of blockchain ecosystems paving the way for a more secure and dependable digital future in the age of decentralised and trustless systems. KEYWORDS Ethereum blockchain, machine learning, anomaly detection, blockchain security, illicit activities ACM Reference Format: Chibuzo Obi-Okoli, Olamide Jogunola, Bamidele Adebisi, and Mohammad Hammoudeh. 2023. Machine Learning Algorithms to Detect Illicit Accountson Ethereum Blockchain. In The International Conference on Future Networksand Distributed Systems (ICFNDS’23), December 21–22, 2023, Dubai, United Arab Emirates. ACM, New York, NY, USA, 6 pages. [https://doi.org/10.1145/](https://doi.org/10.1145/)[ ](https://doi.org/10.1145/)3644713.3644838 1 INTRODUCTION Blockchain technology, initially developed as the backbone for cryptocurrencies like Bitcoin and Ethereum, has a core purpose of reducing the need for centralised intermediaries, such as banks, in financial transactions. Blockchain features, including immutability This work is licensed under a

FAQs

What problem does the paper address on the Ethereum blockchain?

It targets the identification and detection of illicit activities, especially the creation of illicit (fake) accounts, that can undermine trust in blockchain systems.

Which approach is used to deal with imbalanced data?

The work uses the synthetic minority over-sampling technique to mitigate data imbalance and improve classifier performance.

What model performance does the paper report?

It reports that the light gradient boosting machine classifier achieves an accuracy of 98.4%.

Aug 4, 2026

Upload by Noah