Leveraging Ensemble-Based Semi-Supervised Learning for Illicit Account Detection in Ethereum DeFi Transactions

TL;DR

This paper introduces SLEID, an ensemble semi-supervised learning framework that effectively detects illicit Ethereum DeFi accounts by combining outlier detection and self-training, outperforming existing methods.

Contribution

The paper presents a novel ensemble semi-supervised approach using self-training and isolation forest for illicit account detection in Ethereum DeFi transactions, reducing labeled data dependency.

Findings

SLEID achieves +2.56% precision over baselines.

SLEID maintains comparable recall to supervised methods.

SLEID improves F1-score and PR-AUC, especially for minority illicit class.

Abstract

The advent of smart contracts has enabled the rapid rise of Decentralized Finance (DeFi) on the Ethereum blockchain, offering substantial rewards in financial innovation and inclusivity. This growth, however, is accompanied by significant security risks such as illicit accounts engaged in fraud. Effective detection is further limited by the scarcity of labeled data and the evolving tactics of malicious accounts. To address these challenges with a robust solution for safeguarding the DeFi ecosystem, we propose $\textbf{SLEID}$, a $\textbf{S}$elf-$\textbf{L}$earning $\textbf{E}$nsemble-based $\textbf{I}$llicit account $\textbf{D}$etection framework. SLEID uses an Isolation Forest model for initial outlier detection and a self-training mechanism to iteratively generate pseudo-labels for unlabeled accounts, enhancing detection accuracy. Experiments on 6,903,860 Ethereum transactions with extensive DeFi interaction coverage demonstrate that SLEID significantly outperforms supervised and semi-supervised baselines with $\textbf{+2.56}$ percentage-point precision, comparable recall, and $\textbf{+0.90}$ percentage-point F1 -- particularly for the minority illicit class -- alongside $\textbf{+3.74}$ percentage-points higher accuracy and improvements in PR-AUC, while substantially reducing reliance on labeled data.