Scam Detection for Ethereum Smart Contracts: Leveraging Graph Representation Learning for Secure Blockchain

2024-12-16

AI Summary

To address the prevalent fraud in Ethereum smart contracts and the low efficiency and poor generalizability of existing detection methods, this paper proposes a graph representation learning–based fraud detection framework. It models on-chain transaction sequences as heterogeneous transaction graphs and performs graph embedding by jointly encoding node and edge features. To mitigate severe class imbalance, we introduce a novel SMOTE-ENN hybrid sampling strategy. Empirical analysis reveals that a lightweight MLP significantly outperforms GCN in fraud classification—challenging the prevailing reliance on GNNs for graph-based tasks. Extensive experiments demonstrate that our approach achieves superior accuracy, F1-score, and cross-contract generalization compared to state-of-the-art methods. Moreover, it exhibits high scalability and strong potential for real-time deployment.

Technology Category

Machine Learning: Graph-based Machine LearningData Mining & Knowledge Management: Graph Mining, Social Network Analysis & CommunityNatural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphsSecurity and Privacy: Cryptocurrency and smart contractsSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Due to the increasing abuse of fraudulent activities that result in significant financial and reputational harm, Ethereum smart contracts face a significant problem in detecting fraud. Existing monitoring methods typically rely on lease code analysis or physically extracted features, which suffer from scalability and adaptability limitations. In this study, we use graph representation learning to observe purchase trends and find fraudulent deals. We can achieve powerful categorisation performance by using innovative machine learning versions and transforming Ethereum invoice data into graph structures. Our method addresses label imbalance through SMOTE-ENN techniques and evaluates models like Multi-Layer Perceptron ( MLP ) and Graph Convolutional Networks ( GCN). Experimental results show that the MLP type surpasses the GCN in this environment, with domain-specific assessments closely aligned with real-world assessments. This study provides a scalable and efficient way to improve Ethereum's ecosystem's confidence and security.

Problem

• Ethereum Smart Contracts
• Fraud Detection
• Efficiency Issues

Innovation

• Graph Representation Learning
• Machine Learning Techniques (SMOTE-ENN, MLP, GCN)
• Ethereum Smart Contract Fraud Detection