ABSTRACT
The rapid development of blockchain and cryptocurrency in the past decade has created a huge demand for digital trading platforms. Popular decentralised exchanges (DEXs) such as Uniswap and PancakeSwap were created to address this market gap, facilitating cryptocurrency exchange without intermediaries and hence eliminating security and privacy issues associated with traditional centralised platforms. This, however, due to lack of regulation, results in the emergence of a host of damaging investment fraudulent schemes, including Ponzi, honey pot, pump-and-dump, and rug-pull.In this study, we aim to investigate the problem of detecting rug-pull on Uniswap using supervised learning. We aggregate a list of 23 features and propose the use of a hybrid feature selection technique to find the most relevant features for rug-pull. The classifier, using this refined set of features, outperforms the classifier in the previous studies and achieves an f1-score of 99%, a precision of 97% on non-malicious tokens, and a recall of 99% on malicious tokens. Additionally, we show that the XGBoost classifier, built using these proposed features, can distinguish scam tokens and newly listed tokens, which are often harder to differentiate as they have similar characteristics, and also propose a validation method.
- Rachit Agarwal, Tanmay Thapliyal, and Sandeep Kumar Shukla. 2021. Vulnerability and Transaction Behavior Based Detection of Malicious Smart Contracts. In International Symposium on Cyberspace Safety and Security. Springer, Cham, 79–96.Google Scholar
- Becky. 2022. The different types of rug pulls in cryptocurrency scams. https://www.coininsider.com/the-different-types-of-rug-pulls-in-cryptocurrency-scams/. Accessed: 2022-10-01.Google Scholar
- Sunita Beniwal and Jitender Arora. 2012. Classification and Feature Selection Techniques in Data Mining. In International booktitle of Engineering Research & Technology, Vol. 1.6. 1–6.Google Scholar
- Michael Buckland and Fredric Gey. 1994. The relationship between precision and recall. In Journal of the American society for information science, Vol. 45.1. 12–19.Google Scholar
- Jie Cai, Jiawei Luo, Shulin Wang, and ShengYang. 2018. Feature selection in machine learning: A new perspective. In Neurocomputing, Vol. 300. 70–79.Google Scholar
- Chainanalysis. 2021. The 2021 Crypto Crime Report. http://demo.chainalysis.com/2021- crypto-crime-report/. Accessed: 2022-04-24.Google Scholar
- Chainanalysis. 2022. The 2022 Crypto Crime Report. http://demo.chainalysis.com/2022- crypto-crime-report/. Accessed: 2022-04-24.Google Scholar
- Girish Chandrashekar and FeratSahin. 2014. A survey on feature selection methods. In Computers & Electrical Engineering, Vol. 40.1. 16–28.Google Scholar
- Weimin Chen, Xinran Li, Yuting Sui, Ningyu He, Haoyu Wang, Lei Wu, , and Xiapu Luo.2021. Sadponzi: Detecting and characterizing ponzi schemes in ethereum smart contracts. In Proceedings of the ACM on Measurement and Analysis of Computing Systems, Vol. 5.2. 1–30.Google Scholar
- Weili Chen, Zibin Zheng, Jiahui Cui, Edith Ngai, Peilin Zheng, and Yuren Zhou. 2018. Detecting ponzi schemes on ethereum: Towards healthier blockchain technology. In In Proceedings of the 2018 world wide web conference.1409 – 1418.Google ScholarDigital Library
- CoinMarketCap. 2022. CoinMarketCap Ranking List. https://coinmarketcap.com/. Accessed: 2022-10-01.Google Scholar
- CoinMarketCap. 2022. Rug Pull. https://coinmarketcap.com/alexandria/glossary/rug-pull. Accessed: 2022-04-24.Google Scholar
- Nadir Omer Fadl Elssied, Othman Ibrahim, and Ahmed Hamza Osman. 2014. A novel feature selection based on one-way anova f-test for e-mail spam classification. In Research Journal of Applied Sciences, Engineering and Technology, Vol. 7.3. 625–638.Google Scholar
- Etherscan. 2022. Etherscan. https://docs.etherscan.io/. Accessed: 2022-04-24.Google Scholar
- Etherscan. 2022. Token Tracker. https://etherscan.io/tokens/. Accessed: 2022-04-24.Google Scholar
- Sampath Kumar Gajawada. 2019. ANOVA for Feature Selection in Machine Learning. https://towardsdatascience.com/anova-for-feature-selection-in-machine-learning-d9305e228476. Accessed: 2022-10-25.Google Scholar
- Saptarsi Goswami. 2020. Using the Chi-Squared test for feature selection with implementation. https://towardsdatascience.com/using-the-chi-squared-test-for-feature-selection-with-implementation-b15a4dad93f1. Accessed: 2022-10-25.Google Scholar
- Isabelle Guyon and André Elisseeff. 2013. An introduction to variable and feature selection. In booktitle of machine learning research., Vol. 3. 1157–1182.Google Scholar
- Immunefi. 2021. 8 Potential Warning Signs of a Rug Pull. https://medium.com/immunefi/8-potential-warning-signs-of-a-rug-pull-ce3471d09535. Accessed: 2022-10-25.Google Scholar
- Eunjin Jung, Marion Le Tilly, Ashish Gehani, and Yunjie Ge. 2019. Data mining-based ethereum fraud detection. In 2019 IEEE International Conference on Blockchain (Blockchain). 266–273.Google ScholarCross Ref
- Lanlan Liu, Michael Muelly, Jia Deng, Tomas Pfister, and Li-Jia Li. 2019. Generative Modeling for Small-Data Object Detection. Proceedings of the IEEE/CVF International Conference on Computer Vision, 6073–6081.Google ScholarCross Ref
- Manuel Lopez-Martin, Belen Carro, and Antonio Sanchez-Esguevillas. 2019. Variational data generative model for intrusion detection. Knowledge and Information Systems 60.1, 569–590.Google ScholarDigital Library
- Bruno Mazorra, Victor Adan, , and Vanesa Daza. 2022. Do Not Rug on Me: Leveraging Machine Learning Techniques for Automated Scam Detection. In Mathematics., Vol. 10.6. 949.Google Scholar
- Roweida Mohammed, Jumanah Rawashdeh, and Malak Abdullah. 2020. Machine Learning with Oversampling and Undersampling Techniques: Overview Study and Experimental Results. In 11th international conference on information and communication systems (ICICS). IEEE.Google Scholar
- Michael Nofer, Peter Gomber, Oliver Hinz, and Dirk Schiereck. 2017. Blockchain. In Business & Information Systems Engineering, Vol. 59.3. 183–187.Google Scholar
- F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. 2011. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research 12, 2825–2830.Google ScholarDigital Library
- Zheng Peilin, Zheng Zibin, Wu Jiajing, and Dai Hong-ning. 2020. XBlock-ETH: Extracting and Exploring Blockchain Data From Ethereum. In IEEE Open booktitle of the Computer Society, Vol. 1. 95–106.Google Scholar
- Matthew Shardlow.2016. An Analysis of Feature Selection Techniques. In The University of Manchester, Vol. 1. 1–7.Google Scholar
- Mansour Sheikhan, Mahdi Bejani, and Davood Gharavian. 2013. Modular neural-SVM scheme for speech emotion recognition using ANOVA feature selection method. In Neural Computing and Applications, Vol. 23.1. 215–227.Google Scholar
- Uniswap. 2022. Uniswap. https://uniswap.org/. Accessed: 2022-11-23.Google Scholar
- Uniswap. 2022. Uniswap V2 Documentation. https://docs.uniswap.org/. Accessed: 2022-04-24.Google Scholar
- Jorge R. Vergara and Pablo A. Estévez. 2014. A review of feature selection methods based on mutual information. In Chemometrics and Intelligent Laboratory Systems, Vol. 24.1. 175–186.Google Scholar
- Huaimin Wang, Zibin Zheng, Shaoan Xie, and Hong-Ninh Dai.2018. Blockchain challenges and opportunities: a survey. In International journal of web and grid services, Vol. 14.4. 352–375.Google Scholar
- Pengcheng Xia, Haoyu Wang, Bingyu Gao, Weihang Su, Zhou Yu, Xiapu Luo, Chao Zhang, Xusheng Xiao, and Guoai Xu. 2021. Trade or Trick? Detecting and Characterizing Scam Tokens on Uniswap Decentralized Exchange. In Proceedings of the ACM on Measurement and Analysis of Computing Systems., Vol. 5.3. 1–26.Google Scholar
- Reda Yacouby and Dustin Axman. 2020. Probabilistic Extension of Precision, Recall, and F1 Score for More Thorough Evaluation of Classification Models. In Proceedings of the first workshop on evaluation and comparison of NLP systems.Google ScholarCross Ref
Index Terms
- Rug-pull malicious token detection on blockchain using supervised learning with feature engineering
Recommendations
A Flexible Instant Payment System Based on Blockchain
Information Security and PrivacyAbstractImproving the throughput of blockchain systems such as Bitcoin and Ethereum has been an important research problem. Off-chain payments are one of the most promising technologies to tackle this challenge. Once a payment channel, however, is ...
Intrusion Detection and Mitigation System Using Blockchain Analysis for Bitcoin Exchange
CCIOT '18: Proceedings of the 2018 International Conference on Cloud Computing and Internet of ThingsBitcoin exchanges rely heavily on traditional intrusion detection system to secure their system. However, this reliance has proven to be high risk, since Bitcoin and other blockchain-based transactions are not easily reversible. Many of the attacks have ...
Detection and prevention of malicious cryptocurrency mining on internet-connected devices
ICFNDS '18: Proceedings of the 2nd International Conference on Future Networks and Distributed SystemsAs technology evolves, more and more devices are connected to the Internet. The popularity and increasing significance of cryptocurriences are drawing attention, and crybercriminals are trying to utilize the resources and steal the processing power of ...
Comments