Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Ayush Agarwal, Lv Lu, Arjun Maheswaran, Varsha Mahadevan, Bhaskar Krishnamachari

TL;DR

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.

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.

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

TL;DR

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.

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.
Paper Structure (29 sections, 13 figures, 4 tables, 3 algorithms)

This paper contains 29 sections, 13 figures, 4 tables, 3 algorithms.

Table of Contents

  1. INTRODUCTION
  2. Background and Problem Statement
  3. Our Proposed Solution
  4. Node2Vec: Background and Motivation
  5. Our Contributions
  6. Organization of the Paper
  7. RELATED WORK
  8. Risk Scoring of Ethereum Addresses (RiskSEA)
  9. Data Collection and Preprocessing
  10. Feature Extraction
  11. Behavioral Features
  12. Node2Vec Embeddings
  13. Risk Scoring Model
  14. Scaling Node2Vec Embeddings of Blockchain Addresses
  15. Embedding Propagation Methodology
  16. ...and 14 more sections

Figures (13)

  • Figure 1: Risk Scoring of Ethereum Blockchain Addresses (RiskSEA)
  • Figure 2: Embedding Propagation Methodology. Here the colored nodes represent addresses having node2vec embedding (a 1-D vector here) with value equal to the number assigned to them. For the nodes under consideration its randomly picked neighbors are highlighted in bold red outlines.
  • Figure 3: Distributed MapReduce Approach for Generating Random Walks
  • Figure 4: Incremental Training of Node2Vec Embedding Model
  • Figure 5: PR-Curve varying number of walks
  • ...and 8 more figures