Enhancing Ethereum Fraud Detection via Generative and Contrastive Self-supervision

TL;DR

This paper tackles Ethereum fraud detection under imbalanced interaction patterns by introducing meta-interactions and a dual self-supervised framework, Meta-IFD. It combines a generative interaction feature generator (ICVAE) with a multi-view feature learning module and a coarse-grained contrastive module to produce robust account representations on the heterogeneous Ethereum Interaction Graph (HEIG). Through extensive experiments on Ponzi and phishing datasets, Meta-IFD demonstrates superior detection performance and better handling of data imbalance compared to a wide range of baselines, supported by comprehensive ablations. The work offers a scalable, generalizable approach that improves fraud detection while providing practical insights for securing blockchain ecosystems, with code to be released at the authors' repository.

Abstract

The rampant fraudulent activities on Ethereum hinder the healthy development of the blockchain ecosystem, necessitating the reinforcement of regulations. However, multiple imbalances involving account interaction frequencies and interaction types in the Ethereum transaction environment pose significant challenges to data mining-based fraud detection research. To address this, we first propose the concept of meta-interactions to refine interaction behaviors in Ethereum, and based on this, we present a dual self-supervision enhanced Ethereum fraud detection framework, named Meta-IFD. This framework initially introduces a generative self-supervision mechanism to augment the interaction features of accounts, followed by a contrastive self-supervision mechanism to differentiate various behavior patterns, and ultimately characterizes the behavioral representations of accounts and mines potential fraud risks through multi-view interaction feature learning. Extensive experiments on real Ethereum datasets demonstrate the effectiveness and superiority of our framework in detecting common Ethereum fraud behaviors such as Ponzi schemes and phishing scams. Additionally, the generative module can effectively alleviate the interaction distribution imbalance in Ethereum data, while the contrastive module significantly enhances the framework's ability to distinguish different behavior patterns. The source code will be available in https://github.com/GISec-Team/Meta-IFD.

Figures (10)

• Figure 1: Illustration of the imbalanced distribution in account interaction frequency. Various types of accounts display long-tailed distributions for both types of fraud.
• Figure 2: Illustration of meta-path and meta-interaction in heterogeneous Ethereum interaction graph.
• Figure 3: Illustration of the dual self-supervision enhanced Ethereum fraud detection framework (Meta-IFD).
• Figure 4: Illustration of the imbalanced distribution in account interaction types. Boxes indicate the degree correlation statistics for labeled accounts across different interaction types.
• Figure 5: Illustration of the fine-grained Ethereum interaction feature generation module.

Theorems & Definitions (2)

• Definition 1: Heterogeneous Ethereum Interaction Graph, HEIG
• Definition 2: Meta-interactions