Unveiling Latent Information in Transaction Hashes: Hypergraph Learning for Ethereum Ponzi Scheme Detection

2025-03-27

AI Summary

To address the limitation of conventional graph models—which only capture pairwise account transactions and thus struggle to represent multi-party collusive fraud—in Ethereum Ponzi scheme detection, this work introduces, for the first time, an account-transaction hypergraph modeling paradigm: transactions (identified by their hash values) serve as hyperedges explicitly linking all participating accounts. Methodologically, we propose a transaction-hash-driven hyperedge construction mechanism, an adaptive two-step hypergraph sampling strategy to reduce computational overhead, and a dual-channel detection module comprising a hypergraph channel and a hyper-homogeneous graph channel to jointly optimize expressive power and interpretability. Experiments demonstrate that the hyper-homogeneous graph channel achieves an AUC improvement of over 8.2% compared to standard homogeneous graph baselines across multiple real-world datasets, significantly enhancing detection capability for implicit, multi-party fraudulent patterns.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

With the widespread adoption of Ethereum, financial frauds such as Ponzi schemes have become increasingly rampant in the blockchain ecosystem, posing significant threats to the security of account assets. Existing Ethereum fraud detection methods typically model account transactions as graphs, but this approach primarily focuses on binary transactional relationships between accounts, failing to adequately capture the complex multi-party interaction patterns inherent in Ethereum. To address this, we propose a hypergraph modeling method for the Ponzi scheme detection method in Ethereum, called HyperDet. Specifically, we treat transaction hashes as hyperedges that connect all the relevant accounts involved in a transaction. Additionally, we design a two-step hypergraph sampling strategy to significantly reduce computational complexity. Furthermore, we introduce a dual-channel detection module, including the hypergraph detection channel and the hyper-homo graph detection channel, to be compatible with existing detection methods. Experimental results show that, compared to traditional homogeneous graph-based methods, the hyper-homo graph detection channel achieves significant performance improvements, demonstrating the superiority of hypergraph in Ponzi scheme detection. This research offers innovations for modeling complex relationships in blockchain data.

Problem

• Detect Ethereum Ponzi schemes using hypergraph learning
• Model complex multi-party interactions in transaction data
• Reduce computational complexity in fraud detection methods

Innovation

• Hypergraph modeling for Ethereum Ponzi detection
• Two-step hypergraph sampling reduces complexity
• Dual-channel detection module enhances performance