Enhancing Robustness and Accuracy of Ponzi Scheme Detection on Ethereum with Time-Dependent Features

[Submitted on 31 Aug 2023]

Download a PDF of the paper titled “Improving Robustness and Accuracy of Ponzi Scheme Detection on Ethereum Using Time-Dependent Features” by Phuong Duy Huynh and 4 other authors.

Download PDF

Abstract: The rise of blockchain technology has attracted both legitimate investors and cybercriminals. Ponzi schemes, a type of fraud, have become prevalent in the cryptocurrency market, resulting in significant financial losses for many investors. Existing Ponzi detection methods primarily rely on analyzing smart contract source code or opcode, which has limitations in terms of availability and susceptibility to manipulation. In this paper, we propose new detection models that focus on transaction data, providing a more robust approach. By introducing novel time-dependent features derived from comprehensive data analyses, our models achieve higher accuracy, precision, recall, and F1-score compared to existing transaction-based models. The analysis is based on data from the XBlock-ETH repository.