Identity Inference on Blockchain using Graph Neural Network
arXiv:2104.06559 · doi:10.1007/978-981-16-7993-3_1
Abstract
The anonymity of blockchain has accelerated the growth of illegal activities and criminal behaviors on cryptocurrency platforms. Although decentralization is one of the typical characteristics of blockchain, we urgently call for effective regulation to detect these illegal behaviors to ensure the safety and stability of user transactions. Identity inference, which aims to make a preliminary inference about account identity, plays a significant role in blockchain security. As a common tool, graph mining technique can effectively represent the interactive information between accounts and be used for identity inference. However, existing methods cannot balance scalability and end-to-end architecture, resulting high computational consumption and weak feature representation. In this paper, we present a novel approach to analyze user's behavior from the perspective of the transaction subgraph, which naturally transforms the identity inference task into a graph classification pattern and effectively avoids computation in large-scale graph. Furthermore, we propose a generic end-to-end graph neural network model, named , which can accept subgraph as input and learn a function mapping the transaction subgraph pattern to account identity, achieving de-anonymization. Extensive experiments on EOSG and ETHG datasets demonstrate that the proposed method achieve the state-of-the-art performance in identity inference.
arXiv commentUnder review. Blockchain and Trustworthy Systems (BlockSys 2021). Springer, Singapore, 2021
References in corpus (14)
- DeepWalk: Online Learning of Social Representations
- Semi-Supervised Classification with Graph Convolutional Networks
- Neural Message Passing for Quantum Chemistry
- graph2vec: Learning Distributed Representations of Graphs
- Do the rich get richer? An empirical analysis of the BitCoin transaction network
- Detecting Mixing Services via Mining Bitcoin Transaction Network with Hybrid Motifs
- On the Ethereum Blockchain Structure: a Complex Networks Theory Perspective
- NetLSD: Hearing the Shape of a Graph
- Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics
- T-EDGE: Temporal WEighted MultiDiGraph Embedding for Ethereum Transaction Network Analysis
- Anomaly Detection in the Bitcoin System - A Network Perspective
- A Simple Baseline Algorithm for Graph Classification
- Evolution of Ethereum: A Temporal Graph Perspective
- Identifying Illicit Accounts in Large Scale E-payment Networks -- A Graph Representation Learning Approach
Cited by in corpus (6)
- Behavior-aware Account De-anonymization on Ethereum Interaction Graph
- Demystifying Fraudulent Transactions and Illicit Nodes in the Bitcoin Network for Financial Forensics
- BERT4ETH: A Pre-trained Transformer for Ethereum Fraud Detection
- Graph Mining for Cybersecurity: A Survey
- SoK: A Taxonomy for Distributed-Ledger-Based Identity Management
- TEGDetector: A Phishing Detector that Knows Evolving Transaction Behaviors