Fraud Detection in Smart Contracts Anomaly Detection

Zeyuan Lyu

2024

Abstract

Fraud detection is nowadays a critical issue in the blockchain domain, particularly due to the increasing volume of transactions and the associated risks of fraudulent activities. This study focuses on detecting fraudulent transactions within the Ethereum network by employing three different machine learning classifiers: logistic regression, random forest, and XGBoost, respectively. This paper trained and tested these models on a dataset composed of various transaction features to assess their performance. After implementing empirical examining, the results revealed that the tree-based models, specifically the random forest and XGBoost classifiers, significantly outperformed logistic regression in detecting fraudulent activities. The superior performance of these models highlights their robustness in handling high-dimensional data, which is often characteristic of blockchain transactions. This study not only confirms the effectiveness of tree-based models in fraud detection but also offers valuable insights for future research in the field, paving the way for more secure and reliable blockchain trading systems.

Paper Citation

in Harvard Style

Lyu Z. (2024). Fraud Detection in Smart Contracts Anomaly Detection. In Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI; ISBN 978-989-758-726-9, SciTePress, pages 462-468. DOI: 10.5220/0013268800004568

in Bibtex Style

@conference{ecai24,
author={Zeyuan Lyu},
title={Fraud Detection in Smart Contracts Anomaly Detection},
booktitle={Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI},
year={2024},
pages={462-468},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013268800004568},
isbn={978-989-758-726-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI
TI - Fraud Detection in Smart Contracts Anomaly Detection
SN - 978-989-758-726-9
AU - Lyu Z.
PY - 2024
SP - 462
EP - 468
DO - 10.5220/0013268800004568
PB - SciTePress