Anomaly and Fraud Detection in Blockchain Networks
Swiss-UAE bilateral research cooperation investigating static and dynamic anomaly detection methods using hybrid approaches and extreme value theory for real-time blockchain security.
Research Overview
Understanding blockchain vulnerabilities through statistical and machine learning approaches
Background
Blockchain networks are increasingly being implemented into healthcare, supply chain, and retail systems, through smart contracts, smart devices, and smart identity management. Although the use of this technology brings with it benefits, it can also still cause problems. A particular problem is derived from the immutability property, which means that fraudulent transactions or transfers of information cannot be reversed.
Rationale
Blockchains can be attacked via a deluge of requests or transactions within a short time span, resulting in the loss of connectivity to the blockchain for users and businesses, or even financial institutions. Therefore, the rapid detection of anomalies from such activities is critical in order to prevent damage from occurring, or correct any damage as soon as possible to reduce the severity of its impact.
Objectives
- Study the problem of anomaly and fraud detection from the perspective of blockchain-based networks
- Further understanding of the sources and behaviours of anomalies and fraud in blockchain-based networks
- Develop new improved methods for both static and dynamic anomaly detection
- Enable real-time fraud detection alongside blockchain-based systems
Methods
- Static Detection: Hybrid K-means clustering combined with Generalized Extreme Value (GEV) distribution
- Dynamic Detection: Streaming data analysis using Generalized Pareto Distribution (GPD) and extreme value theory
- Network Analysis: Comprehensive analysis of blockchain network graphs (Bitcoin, Ethereum, and others)
Expected Impact
The project will be particularly beneficial alongside real world blockchain-based networks to allow for the fast detection of anomalous or fraudulent data, preventing damage or allowing for damage to be corrected as soon as possible. For cryptocurrency networks, this will reduce the impact of market manipulation, fraud, and more widely on global financial markets, currencies, and trade. In addition, the project will be of interest to a broad range of cryptocurrency and blockchain stakeholders including academics, financial institutions, policymakers, regulators, and cybercrime agencies.
Research Team
International collaboration between Switzerland, UAE, UK, China, and Romania
Research Outputs
Key metrics and deliverables from the project
Publications
Peer-reviewed papers and manuscripts from the project
| Year | Title / Authors | Venue | Citations | Links |
|---|---|---|---|---|
| 2024 |
Metaverse non-fungible tokens
|
Financial Innovation (under review) | - | In Review |
| 2024 |
Enhancing security in blockchain networks: Anomalies, frauds, and advanced detection techniques
|
Financial Innovation (under review) | - | In Review |
| 2024 |
Stylized facts of Metaverse Non-Fungible Tokens
|
Physica A: Statistical Mechanics and its Applications (submitted) | - | Submitted |
| 2020 |
Lead behaviour in bitcoin markets
|
Risks, 8(1), 4 | 50+ | DOI |
| 2017 |
GARCH modelling of cryptocurrencies
|
Journal of Risk and Financial Management, 10(4), 17 | 340 | DOI OA |
| 2017 |
A statistical analysis of cryptocurrencies
|
Journal of Risk and Financial Management, 10(2), 12 | 213 | DOI OA |
Datasets & Code
Open-source tools and research data from team members
Research Tools
VaRES R Package
Value at Risk and Expected Shortfall computation package co-developed by Stephen Chan. Essential tool for risk assessment in cryptocurrency portfolios.
View on CRANBlockchain Transaction Dataset
Curated dataset of blockchain transactions for anomaly detection research. Includes labeled examples of normal and anomalous activity.
Request AccessAnomaly Detection Models
Python implementations of hybrid anomaly detection methods combining K-means clustering with extreme value distributions.
GitHubReal-time Risk Rating System
Dashboard for real-time risk assessment of digital assets. Showcased at AUS Innovation Expo 2024 and Hong Kong Laureate Forum 2023.
Request DemoAcademic Events
Conferences, seminars, and workshops
Media Coverage
Press releases and industry recognition
Collaborations
Academic and industry partnerships
Academic Partners
American University of Sharjah
UAE - Mathematics and Statistics Department
Bern University of Applied Sciences
Switzerland - Business School
University of Twente
Netherlands - Faculty of BMS
University of Manchester
UK - Alliance Manchester Business School
Renmin University of China
China - School of Statistics
Babes-Bolyai University
Romania - Faculty of Economics
Related Networks & Projects
MSCA DIGITAL Network
EUR 4.5M - Industrial Doctoral Network on Digital Finance
COST Action CA19130
FinAI - Fintech and AI in Finance (Action Chair: Prof. Osterrieder)
Society of Actuaries
Research Institute - DeFi for Actuaries Project
Funding
Research grants supporting this project
| Grant | PI | Funder | Amount | Period |
|---|---|---|---|---|
| SNF Scientific Exchanges | Joerg Osterrieder | Swiss National Science Foundation | CHF 6,700 | 2023 |
| Faculty Research Grant 2023 (FRG23) | Stephen Chan | American University of Sharjah | AED 248,000 | 2023-2025 |
| Faculty Research Grant 2024 (FRG24) | Stephen Chan | American University of Sharjah | AED 25,000 | 2024-2025 |
| Centre for Digital Trust and Society Seed Corn Funding | Yuanyuan Zhang | University of Manchester | GBP 8,560 | 2023-2024 |
| Leading House MENA Research Partnership | Joerg Osterrieder | Swiss State Secretariat | - | 2021, 2022, 2023 |
| China Leading House | Joerg Osterrieder | Swiss State Secretariat | - | 2023, 2024 |
Follow-up Projects
Building on the Scientific Exchange foundation
International Workshop Series on Blockchain and Digital Finance
An annual international workshop series will be initiated, rotating among the partner institutions, starting in 2025. These workshops will focus on emerging trends in blockchain technology, digital finance, and their societal impacts, aiming to foster ongoing dialogue and collaboration among international researchers and practitioners.
NSF-SNF Joint Research Application (2025-2026)
A joint research application to the National Science Foundation (NSF) in the United States and the Swiss National Science Foundation (SNF) is planned for 2025-2026. This application will focus on securing funding for a project that explores innovative solutions in blockchain technology and digital finance, leveraging the expertise and research findings from the collaborative efforts.
MSCA Industrial Doctoral Network on Digital Finance
The partners involved in the Scientific Exchange are also working together within the framework of the Marie Sklodowska-Curie Actions Industrial Doctoral Network on Digital Finance. This collaboration focuses on the development of a doctoral training program that combines academic research with industry experience, providing PhD candidates with a comprehensive understanding of digital finance, including blockchain technology, cryptocurrencies, and financial data science.
MSc Course Contribution: Digital Finance
As part of the ongoing collaborations, Stephen Chan will contribute his expertise by teaching in a Master of Science course focused on digital finance, disseminating research findings to the next generation of finance professionals.
Contact
Get in touch with the research team
Principal Investigator
Prof. Dr. Joerg Osterrieder
Bern University of Applied Sciences
Bruckenstrasse 73, 3005 Bern, Switzerland
Co-Principal Investigator
Prof. Dr. Stephen Chan
American University of Sharjah
P.O. Box 26666, Sharjah, UAE