Comparative Analysis of Machine Learning Based Fraud Detection Techniques In Blockchain

Sabih Hida Tahir; Muhammad Raza; Ageshwari Haryani; Almina Sherish

doi:10.1109/ICCMC51019.2021.9418470

Author(s)

Sabih Hida Tahir SZABIST University, Karachi Campus , Pakistan

Sabih Hida Tahir SZABIST University, Gharo Campus Country, Pakistan

Muhammad Raza SZABIST University, Karachi Campus , Pakistan

Ageshwari Haryani SZABIST University, Karachi Campus , Pakistan

Almina Sherish SZABIST University, Karachi Campus , Pakistan

Abstract

Fraudulent activities like phishing and pumpdump schemes clearly threaten the integrity and reliability of decentralized platforms, especially Ethereum. This paper compares the quality of fraud detection methods in Ethereum's platform. It emphasizes the potential of unsupervised and supervised learning algorithms applied to Ethereum. The aim is to have an advanced system capable of firmly protecting Ethereum by detecting fraud and putting a stop to it. This paper collected transactional data on Ethereum, smart contract interactions, and past fraud activities possibly significant to net miners. It further proposed fine-grained features targeting Ethereum transaction nuances, which are important early signs of fraud. The paper takes an integrated approach in comparing traditional supervised methods such as Random Forest, eXtreme Gradient Boosting, Decision Trees, K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Naive Bayes, Logistic Regression, and Linear Discriminant Analysis (LDA), versus unsupervised learning like outlier detection or clustering algorithms such as K-Means, Gaussian Mixture Models (GMM), and BIRCH. Unlike most Ethereum fraud detection studies that rely heavily on supervised techniques, this one highlights the lack of unsupervised techniques and shifts the spotlight to a comparative analysis with three unsupervised algorithms. In addition, this paper also compares the algorithms on time efficiency. Benchmarking with traditional supervised techniques indicates that unsupervised learning is more effective in detecting new fraudulent patterns. Overall evaluation was further broken down under headings of precision, recall, F1-score and Silhouette score. It proposes a proactive fraud prevention system for Ethereum, having foreseen an event before it actually happens. The goal is to maintain security in Ethereum, as well as other decentralized networks, providing flexible defenses against this rapidly evolving form of crime.

Publication Details

Page(s) 52-65

DOI 10.1109/ICCMC51019.2021.9418470

Published Journal: Journal of Information & Communication Technology (JICT), Volume: 18, Issue: 1, Year: 2024

Request the full text from PASTIC

Keywords

Unsupervised Learning, Fraud Detection, Anomaly detection, Comparative Analysis, Cryptocurrency, Ethereum Network, Proactive Security, Blockchain Security

References

Chen Weixian,Pan. Weixian .2018 .“When Machine Learning Meets Blockchain: A Decentralized, Privacy-preserving and Secure Design. , 8622598 : 10-1187.

Chen Y.,Sun J.,Yang Y.,Li T.,Niu X.,Zhou H. .2021 .PSSPR: a source location privacy protection scheme based on sector phantom routing in WSNs. International Journal of Intelligent Systems, 37 : .

Duan Yong.,Countermeasures Their .2022 .“Multiple-Layer Security Threats on the Ethereum Blockchain. Security and Communication Networks”, 10 : .

Lee G.,Howard D.,Ślęzak Y.S.. .2012 .. Communications in Computer and Information Science: Preface, : .

Stefánsson ,- ,- .2022 .Detecting potential money laundering addresses in the Bitcoin blockchain using unsupervised machine learning”. , : .

Kim Hyoung. .2018 .“Intrusion Detection and Mitigation System Using Blockchain Analysis for Bitcoin” Exchange. , : 10-44.

Duan Li,Article ID .2022 .MultipleLayer Security Threats on the Ethereum Blockchain and Their Countermeasures”. Security and Communication Networks, : .

He Xuezhi,Tan Yang Xuezhi,Liping Chen Xuezhi .2022 .. , : .

Bhowmik M.,Rudra B. .2021 .Comparative Study of Machine Learning Algorithms for Fraud Detection in Blockchain,” 2021 5th International Conference on Computing Methodologies and Communication (ICCMC), Erode. , : .

Zeljko. .2020 .Detection: Classification of Skewed Data. Detecting Malicious Ethereum Entities via Application of Machine Learning Classification. 120-127. 10.1109/ BRAINS49436, 9223304 : 50-59.

Lorenz Joana .2021 .Detecting potential money laundering addresses in the Bitcoin blockchain using unsupervised machine learning. , : .

Phua Vincent. .2004 .“Minority Report in Fraud Detection: Classification of Skewed Data”. SIGKDD Explorations, 6 : 50-59.

Goutte Eric. .2005 .A Probabilistic Interpretation of Precision, Recall and F-Score, with Implication for Evaluation. Lecture Notes in Computer Science, 3408 : 25-359.

Rousseeuw Peter. .1987 .“A Graphical Aid to the Interpretation and Validation of Cluster Analysis”. Journal of Computational and Applied Mathematics, 20(87) : 90125-7.

Saxena Rohit .2023 .Classifying Transactional Addresses using Supervised Learning Approaches over Ethereum Blockchain”. , 01 : .

Lorenz Joana . .Machine learning methods to detect money laundering in the bitcoin blockchain in the presence of label scarcity”. , : .

Kim Hyoung. .2018 .“Intrusion Detection and Mitigation System Using Blockchain Analysis for Bitcoin Exchange”. , : 10-44.

Huang Qichen.,Implementation Qichen. .2023 .. , : .

. .. and Technology, 41 : 6804-182.

Aziz .2024 .“Ethereum Fraud Detection Using Various Machine Learning Models. International Research Journal of Engineering and Technology (IRJET), 11 : 846-852.

Xiong Ao .2023 .. Blockchain Abnormal Transaction Detection Method Based on Auto-encoder and Attention Mechanism”, 30 May, 2969521 : .

Obi-Okoli Chibuzo,Hammoudeh Mohammad .2024 .Association for Computing Machinery. In Proceedings of the 7th International Conference on Future Networks and Distributed Systems (ICFNDS '23), : 747-752.

Agarwal Udit .2023 .. Mano Yadav, 07 December, : .