Detecting Ponzi Schemes on Ethereum: Towards Healthier Blockchain Technology
Blockchain technology becomes increasingly popular. It also attracts scams, for example, Ponzi scheme, a classic fraud, has been found making a notable amount of money on Blockchain, which has a very negative impact. To help dealing with this issue, we propose an approach to detect Ponzi schemes on Blockchain by using data mining and machine learning methods. By verifying smart contracts on Ethereum, we first extract features from user accounts and operation codes of the smartcontracts and then build a classification model to detect latent Ponzi schemes implemented as smart contracts. Using the manually checked samples and XGBoost, a regression tree model based on extracted account features and code features is build. The experimental results indicate that the proposed model has high accurate and can be used to detect latent smart Ponzi schemes in practice. The most significance results are that using our extracted code features that are publicly accessible in any running contract, is enough to build a practical model for detecting Ponzi scheme contract at the moment of its creation. In addition, we estimate that there are more than 400 smart Ponzi schemes on Ethereum, which are far more than the previous estimation. Based on these results, we propose to build a uniform platform to evaluate and monitor every created smart contract for early warning of scams.
In the future, we are going to further this study in three aspects. Firstly, to extend the ground truth data and improve the classification model. As the number of smart contracts having source codes keep increasing every day, it is possible to extend the ground truth data by manually checking the source codes. With more ground truth data, more accurate and credible model can be developed. Secondly, to build a unified platform to evaluate and score every smart contract for every possible scam. We have noticed that there is an open source project on Github to keep track of all the current Ethereum scams17. However, the website collects data by manual user reports and combines them. We are trying to establish a similar website focusing on detecting smart contracts by data mining methods. Thirdly, to study other kinds of scams. Except for smart Ponzi scheme, many other scams are taking the advantage of Blockchain technology. It is necessary to study this question to promote the development of Blockchain technology.
ICSE-SEIP: A Detailed and Real-time Performance Monitoring Framework for Blockchain Systems
Our alicloud server had been rebooted by some issues on June 27th. You can Google or Baidu it...Thus some of the services are shutdown T-T.
We will try to reboot the services on this website ASAP. Some results of the paper will be uploaded with a link in Dropbox ASAP, too T_T. Thank you!