Anomaly and Fraud Detection in Blockchain Networks
Swiss National Science Foundation | CHF 300K | 2019-2022 —
Overview
SNSF-funded international research collaboration developing methods for detecting anomalies and fraud in blockchain-based and cryptocurrency networks.
Grant Number: IZSEZ0_211195
Role
Principal Investigator - Led international research team across multiple institutions.
Research Team
- Prof. Stephen Chan (American University of Sharjah)
- Dr. Yuanyuan Zhang (University of Manchester)
- Prof. Jeffrey Chu (Renmin University)
- Prof. Codruta Mare (Babes-Bolyai University)
- Prof. Branka Hadji Misheva (Bern Business School)
Research Focus
Despite blockchain advantages (transparency, immutability, decentralization), networks remain susceptible to:
- Transaction anomalies
- Smart contract vulnerabilities
- Fraud schemes
- Network attacks
Detection Methods
| Category | Techniques |
|---|---|
| Statistical Methods | Outlier detection, change point analysis |
| Machine Learning | Supervised classification, unsupervised clustering |
| Game Theory | Incentive mechanism design |
| Digital Forensics | Transaction tracing, wallet clustering |
| Reputation Systems | Trust scoring, behavioral analysis |
Key Publications
- arXiv (2024): Enhancing Security in Blockchain Networks: Anomalies, Frauds, and Advanced Detection Techniques
- SSRN: A Primer on Anomaly and Fraud Detection in Blockchain Networks
Project Completion
Successfully completed in 2024 with methods and techniques that make it easier to deal with digital finance challenges and highlight the need for innovative regulatory approaches.