Data Mining for Detecting Bitcoin Ponzi Schemes

Soon after its introduction in 2009, Bitcoin has been adopted by cyber-criminals, which rely on its pseudonymity to implement virtually untraceable scams. One of the typical scams that operate on Bitcoin are the so-called Ponzi schemes. These are fraudulent investments which repay users with the funds invested by new users that join the scheme, and implode when it is no longer possible to find new investments. Despite being illegal in many countries, Ponzi schemes are now proliferating on Bitcoin, and they keep alluring new victims, who are plundered of millions of dollars. We apply data mining techniques to detect Bitcoin addresses related to Ponzi schemes. Our starting point is a dataset of features of real-world Ponzi schemes, that we construct by analysing, on the Bitcoin blockchain, the transactions used to perform the scams. We use this dataset to experiment with various machine learning algorithms, and we assess their effectiveness through standard validation protocols and performance metrics. The best of the classifiers we have experimented can identify most of the Ponzi schemes in the dataset, with a low number of false positives.

[1]  William W. Cohen.  Fast Effective Rule Induction , 1995, ICML.

[2]  Steven Lee,et al.  Anomaly Detection in Bitcoin Network Using Unsupervised Learning Methods , 2016, ArXiv.

[3]  Marc Artzrouni,et al.  The mathematics of Ponzi schemes , 2009, Math. Soc. Sci..

[4]  Günter Müller,et al.  Economic Analysis of Cryptocurrency Backed Money Laundering , 2015, ECIS.

[5]  Anna Cinzia Squicciarini,et al.  Toward De-Anonymizing Bitcoin by Mapping Users Location , 2015, CODASPY.

[6]  Tyler Moore,et al.  The Postmodern Ponzi Scheme: Empirical Analysis of High-Yield Investment Programs , 2012, Financial Cryptography.

[7]  Jeremy Clark,et al.  Mixcoin: Anonymity for Bitcoin with Accountable Mixes , 2014, Financial Cryptography.

[8]  Lars Schmidt-Thieme,et al.  Cost-sensitive learning methods for imbalanced data , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[9]  Rainer Böhme,et al.  Anonymous Alone? Measuring Bitcoin’s Second-Generation Anonymization Techniques , 2017, 2017 IEEE European Symposium on Security and Privacy Workshops (EuroS&PW).

[10]  Jeremy Clark,et al.  SoK: Research Perspectives and Challenges for Bitcoin and Cryptocurrencies , 2015, 2015 IEEE Symposium on Security and Privacy.

[11]  Niall M. Adams,et al.  Transaction aggregation as a strategy for credit card fraud detection , 2009, Data Mining and Knowledge Discovery.

[12]  Stefano Bistarelli,et al.  Visualizing Bitcoin Flows of Ransomware: WannaCry One Week Later , 2018, ITASEC.

[13]  P. Takis Mathiopoulos,et al.  Identification of High Yielding Investment Programs in Bitcoin via Transactions Pattern Analysis , 2017, GLOBECOM 2017 - 2017 IEEE Global Communications Conference.

[14]  Jon T. S. Quah,et al.  Real Time Credit Card Fraud Detection using Computational Intelligence , 2007, 2007 International Joint Conference on Neural Networks.

[15]  Tyler Moore,et al.  The promise and perils of digital currencies , 2013, Int. J. Crit. Infrastructure Prot..

[16]  Massimo Bartoletti,et al.  A general framework for blockchain analytics , 2017, SERIAL@Middleware.

[17]  Nitesh V. Chawla,et al.  Editorial: special issue on learning from imbalanced data sets , 2004, SKDD.

[18]  Anazida Zainal,et al.  Fraud detection system: A survey , 2016, J. Netw. Comput. Appl..

[19]  Ghassan O. Karame,et al.  Evaluating User Privacy in Bitcoin , 2013, Financial Cryptography.

[20]  Adam Doupé,et al.  Behind closed doors: measurement and analysis of CryptoLocker ransoms in Bitcoin , 2016, 2016 APWG Symposium on Electronic Crime Research (eCrime).

[21]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[22]  Hannes Hartenstein,et al.  Could Network Information Facilitate Address Clustering in Bitcoin? , 2017, Financial Cryptography Workshops.

[23]  Taghi M. Khoshgoftaar,et al.  Experimental perspectives on learning from imbalanced data , 2007, ICML '07.

[24]  Siddhartha Bhattacharyya,et al.  Data mining for credit card fraud: A comparative study , 2011, Decis. Support Syst..

[25]  Lior Rokach,et al.  Decision forest: Twenty years of research , 2016, Inf. Fusion.

[26]  Tyler Moore,et al.  There's No Free Lunch, Even Using Bitcoin: Tracking the Popularity and Profits of Virtual Currency Scams , 2015, Financial Cryptography.

[27]  Vukosi N. Marivate,et al.  Unsupervised learning for robust Bitcoin fraud detection , 2016, 2016 Information Security for South Africa (ISSA).

[28]  T. Slattery.  Taking a Bit out of Crime: Bitcoin and Cross-Border Tax Evasion , 2014 .

[29]  Rainer Böhme,et al.  The price of anonymity: empirical evidence from a market for Bitcoin anonymization , 2017, J. Cybersecur..

[30]  Tyler Moore,et al.  Analyzing the Bitcoin Ponzi Scheme Ecosystem , 2018, Financial Cryptography Workshops.

[31]  Rainer Böhme,et al.  Towards Risk Scoring of Bitcoin Transactions , 2014, Financial Cryptography Workshops.

[32]  Satoshi Nakamoto.  Bitcoin : A Peer-to-Peer Electronic Cash System , 2009 .

[33]  Klaus Wehrle,et al.  Secure and anonymous decentralized Bitcoin mixing , 2018, Future Gener. Comput. Syst..

[34]  Zibin Zheng,et al.  Detecting Ponzi Schemes on Ethereum: Towards Healthier Blockchain Technology , 2018, WWW.

[35]  Massimo Bartoletti,et al.  Dissecting Ponzi schemes on Ethereum: identification, analysis, and impact , 2017, Future Gener. Comput. Syst..

[36]  Fergal Reid,et al.  An Analysis of Anonymity in the Bitcoin System , 2011, PASSAT 2011.

[37]  Alex Biryukov,et al.  Bitcoin over Tor isn't a Good Idea , 2014, 2015 IEEE Symposium on Security and Privacy.

[38]  Malte Möser,et al.  An inquiry into money laundering tools in the Bitcoin ecosystem , 2013, 2013 APWG eCrime Researchers Summit.

[39]  S A R A H M E I K L E J O H N,et al.  A Fistful of Bitcoins Characterizing Payments Among Men with No Names , 2013 .

[40]  Miguel Costa,et al.  A data mining based system for credit-card fraud detection in e-tail , 2017, Decis. Support Syst..

[41]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[42]  Stefano Zanero,et al.  BitIodine: Extracting Intelligence from the Bitcoin Network , 2014, Financial Cryptography.

[43]  Niall M. Adams,et al.  Plastic card fraud detection using peer group analysis , 2008, Adv. Data Anal. Classif..

[44]  Gianluca Bontempi,et al.  Learned lessons in credit card fraud detection from a practitioner perspective , 2014, Expert Syst. Appl..