Data Mining for Detecting Bitcoin Ponzi Schemes

@article{Bartoletti2018DataMF,
  title={Data Mining for Detecting Bitcoin Ponzi Schemes},
  author={Massimo Bartoletti and Barbara Pes and Sergio Serusi},
  journal={2018 Crypto Valley Conference on Blockchain Technology (CVCBT)},
  year={2018},
  pages={75-84}
}
Soon after its introduction in 2009, Bitcoin has been adopted by cyber-criminals, which rely on its pseudonymity to implement virtually untraceable scams. [...] Key Method 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…Expand
Data Mining-Based Ethereum Fraud Detection
TLDR
This work uses data mining to provide a detection model for Ponzi schemes on Ethereum, improving over prior work, and built a dataset of likely benign Ethereum smart contracts, in addition to known Ponzis, and designed features based on their compiled code and transactions. Expand
Machine learning methods to detect money laundering in the bitcoin blockchain in the presence of label scarcity
TLDR
This work shows that existing state-of-the-art solutions using unsupervised anomaly detection methods are inadequate to detect the illicit patterns in a real Bitcoin transaction dataset, and shows that the proposed active learning solution is capable of matching the performance of a fully supervised baseline by using just 5\% of the labels. Expand
Supervised learning model for identifying illegal activities in Bitcoin
TLDR
The proposed ensemble of decision trees for supervised learning model provided a reliable tool for forensic study and showed the specificity and sensitivity of the proposed model were comparable to other models. Expand
Bitcoin Concepts, Threats, and Machine-Learning Security Solutions
TLDR
This survey paper conducts an intensive study that explores key security concerns of the Bitcoin system and its main technologies including the blockchain protocol, and details the existing threats and weaknesses of the system. Expand
Ponzi Scheme Detection in EthereumTransaction Network
TLDR
This paper first collects target contracts’ transactions to establish transaction networks and proposes a detecting model based on graph convolutional network (GCN) to precisely distinguish Ponzi contracts, which has caused large property damage to the users in Ethereum. Expand
Detecting Illicit Entities in Bitcoin using Supervised Learning of Ensemble Decision Trees
TLDR
Empirical evaluation of the proposed ensemble of decision trees for supervised learning model showed that the specificity and sensitivity of the model were comparable to other models, and provided a reliable tool for forensic study. Expand
Cascading Machine Learning to Attack Bitcoin Anonymity
TLDR
A method to attack Bitcoin anonymity is presented, leveraging a novel cascading machine learning approach that requires only a few features directly extracted from Bitcoin blockchain data. Expand
An Evaluation of Bitcoin Address Classification based on Transaction History Summarization
TLDR
New features in addition to those commonly used in the literature to build a classification model for detecting abnormality of Bitcoin network addresses are proposed including various high orders of moments of transaction time (represented by block height) which summarizes the transaction history in an efficient way. Expand
Anomaly Detection in Bitcoin Prices using DBSCAN Algorithm
Blockchain is an emerging technology which is also behind the Bitcoin digital money. Daily bitcoin transactions are increasing due to the popular and widespread investments. The increase of BitcoinExpand
Characterizing and Detecting Money Laundering Activities on the Bitcoin Network
TLDR
This paper creates transaction graphs and provides an in-depth analysis on various graph characteristics to differentiate money laundering transactions from regular transactions and proposes and evaluates a set of classifiers based on four types of graph features: immediate neighbours, curated features, deepwalk embeddings, and node2vecembeddings to classify money laundering and regular transactions. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 45 REFERENCES
Detecting Ponzi Schemes on Ethereum: Towards Healthier Blockchain Technology
TLDR
By verifying smart contracts on Ethereum, this paper first extracts features from user accounts and operation codes of the smart contracts and then builds a classification model to detect latent Ponzi schemes implemented as smart contracts, and shows that the proposed approach can achieve high accuracy for practical use. Expand
An inquiry into money laundering tools in the Bitcoin ecosystem
TLDR
A first systematic account of opportunities and limitations of anti-money laundering (AML) in Bitcoin, a decentralized cryptographic currency proliferating on the Internet, is provided and it appears unlikely that a Know-Your-Customer principle can be enforced in the Bitcoin system. Expand
BitIodine: Extracting Intelligence from the Bitcoin Network
TLDR
A modular framework, BitIodine, which parses the blockchain, clusters addresses that are likely to belong to a same user or group of users, classifies such users and labels them, and finally visualizes complex information extracted from the Bitcoin network is presented. Expand
Analyzing the Bitcoin Ponzi Scheme Ecosystem
TLDR
The supply and demand for Bitcoin-based Ponzi schemes is analyzed to identify factors that affect scam persistence and finds that scams are shorter-lived when the scammers register their account on the same day that they post about their scam. Expand
Identification of High Yielding Investment Programs in Bitcoin via Transactions Pattern Analysis
TLDR
This paper proposes a number of features that can be extracted from transactions in Bitcoin that are based upon relating Bitcoin addresses with graph mining procedures and shows that about 83% of HYIP addresses are correctly classified while maintaining false positive rate less than 4.4%. Expand
Unsupervised learning for robust Bitcoin fraud detection
TLDR
This paper investigates the use of trimmed k-means, that is capable of simultaneous clustering of objects and fraud detection in a multivariate setup, to detect fraudulent activity in Bitcoin transactions. Expand
There's No Free Lunch, Even Using Bitcoin: Tracking the Popularity and Profits of Virtual Currency Scams
TLDR
The first empirical analysis of Bitcoin-based scams: operations established with fraudulent intent is presented, finding that at least $11 million has been contributed to the scams from 13 000 distinct victims. Expand
Anomaly Detection in Bitcoin Network Using Unsupervised Learning Methods
TLDR
Three unsupervised learning methods including k-means clustering, Mahalanobis distance, and Unsupervised Support Vector Machine are used on two graphs generated by the Bitcoin transaction network to detect which users and transactions are the most suspicious. Expand
Dissecting Ponzi schemes on Ethereum: identification, analysis, and impact
TLDR
A comprehensive survey of Ponzi schemes on Ethereum, analysing their behaviour and their impact from various viewpoints shows that they still make users lose money, but at least are guaranteed to execute "correctly". Expand
The promise and perils of digital currencies
  • T. Moore
  • Business, Computer Science
  • Int. J. Crit. Infrastructure Prot.
  • 2013
TLDR
The Costa-Rica-based digital currency, Liberty Reserve, was closed down because it allegedly laundered more than $6 billion on behalf of cyber criminals who had turned to the currency as a favored means of exchange. Expand
...
1
2
3
4
5
...