Investigating the impact of structural and temporal behaviors in Ethereum phishing users detection

Abstract

The recent surge of Ethereum in prominence has made it an attractive target for various kinds of crypto crimes. Phishing scams, for example, are an increasingly prevalent cybercrime in which malicious users attempt to steal funds from a user's crypto wallet. This research investigates the effects of network architectural features as well as the temporal aspects of user activities on the performance of detecting phishing users on the Ethereum transaction network. We employ traditional machine learning algorithms to evaluate our model on real-world Ethereum transaction data. The experimental results demonstrate that our proposed features identify phishing accounts efficiently and outperform the baseline models by 4% in Recall and 5% in F1-score.