RiskSEA : A Scalable Graph Embedding for Detecting On-chain Fraudulent Activities on the Ethereum Blockchain

TL;DR

RiskSEA is a scalable graph embedding system designed to detect on-chain fraudulent activities on Ethereum by combining node2vec embeddings with behavioral features, effectively handling large-scale, dynamic blockchain data.

Contribution

The paper introduces novel scalable methods for generating node2vec embeddings in dynamic blockchain graphs and integrates them with behavioral features for improved fraud detection.

Findings

Dynamic node2vec embeddings outperform propagated embeddings.

Combining behavioral and embedding features enhances classification accuracy.

RiskSEA effectively handles large-scale, evolving blockchain transaction graphs.

Abstract

Like any other useful technology, cryptocurrencies are sometimes used for criminal activities. While transactions are recorded on the blockchain, there exists a need for a more rapid and scalable method to detect addresses associated with fraudulent activities. We present RiskSEA, a scalable risk scoring system capable of effectively handling the dynamic nature of large-scale blockchain transaction graphs. The risk scoring system, which we implement for Ethereum, consists of 1. a scalable approach to generating node2vec embedding for entire set of addresses to capture the graph topology 2. transaction-based features to capture the transactional behavioral pattern of an address 3. a classifier model to generate risk score for addresses that combines the node2vec embedding and behavioral features. Efficiently generating node2vec embedding for large scale and dynamically evolving blockchain transaction graphs is challenging, we present two novel approaches for generating node2vec embeddings and effectively scaling it to the entire set of blockchain addresses: 1. node2vec embedding propagation and 2. dynamic node2vec embedding. We present a comprehensive analysis of the proposed approaches. Our experiments show that combining both behavioral and node2vec features boosts the classification performance significantly, and that the dynamic node2vec embeddings perform better than the node2vec propagated embeddings.