Near Real-Time Ethereum Fraud Detection Using Explainable AI in Blockchain Networks
Source abstract
Abstract
Blockchain technologies have profoundly transformed information systems by providing decentralized infrastructures that enhance transparency, security, and traceability. Ethereum, in particular, supports smart contracts and facilitates the development of decentralized finance (DeFi), non-fungible tokens (NFTs), and Web3 applications. However, its openness also enables illicit activities, including fraud and money laundering, through anonymous wallets. Identifying wallets involved in large transfers or abnormal transactional patterns is therefore critical to ecosystem security. This study proposes an AI-based framework employing XGBoost, LightGBM, and CatBoost to detect suspicious Ethereum wallets, achieving test accuracies between 95.83% and 96.46%. The system provides near real-time predictions for individual or recent wallet addresses using a pre-trained XGBoost model. To improve interpretability, SHAP (SHapley Additive exPlanations) visualizations are integrated, highlighting the contribution of each feature. The results demonstrate the effectiveness of AI-driven methods in monitoring and securing Ethereum transactions against fraudulent activities.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Blockchain Technology Applications and Security · Imbalanced Data Classification Techniques · Electricity Theft Detection Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Digital Forensics Engineering, Technology Faculty, Firat University, 23200 Elazığ, Türkiye
Funding
Scientific Research Projects Coordination Unit of Firat University, Türkiye
References (37)
Show source-provided references
1. A systematic review of blockchain10.1186/s40854-019-0147-z ↗
2. AI-enhanced blockchain technology: A review of advancements and opportunities10.1016/j.jnca.2024.103858 ↗
3. Ethereum fraud detection via joint transaction language model and graph representation learning10.1016/j.inffus.2025.103074 ↗
4. Emerging trends in blockchain technology and applications: A review and outlook10.1016/j.jksuci.2022.03.007 ↗
5. Dappscan: Building large-scale datasets for smart contract weaknesses in dapp projects10.1109/TSE.2024.3383422 ↗
6. Accounting and auditing with blockchain technology and artificial Intelligence: A literature review10.1016/j.accinf.2022.100598 ↗
7. A comprehensive review of blockchain technology: Underlying principles and historical background with future challenges10.1016/j.dajour.2023.100344 ↗
8. Security reinforcement for Ethereum virtual machine10.1016/j.ipm.2021.102565 ↗
9. Defiranger: Detecting DeFI price manipulation attacks10.1109/TDSC.2023.3346888 ↗
10. A comparative analysis of the platforms for decentralized autonomous organizations in the Ethereum blockchain10.1186/s13174-021-00139-6 ↗
11. Li, S., Gou, G., Liu, C., Xiong, G., Li, Z., Xiao, J., and Xing, X. (2023, January 4–8). TGC: Transaction Graph Contrast Network for Ethereum Phishing Scam Detection. Proceedings of the 39th Annual Computer Security Applications Conference, Austin, TX, USA.10.1145/3627106.3627109 ↗
12. Toward understanding asset flows in crypto money laundering through the lenses of Ethereum heists10.1109/TIFS.2023.3346276 ↗
13. Money laundering through cryptocurrencies-analysis of the phenomenon and appropriate prevention measures10.1108/JMLC-02-2021-0017 ↗
14. Chainalysis, T. (2025, May 19). The Chainalysis 2025 Crypto Crime Report. Available online: https://go.chainalysis.com/2025-Crypto-Crime-Report.html.
15. Chen, Z., Hu, Y., He, B., Luo, D., Wu, L., and Zhou, Y. (2024). Dissecting payload-based transaction phishing on Ethereum. arXiv.10.14722/ndss.2025.230311 ↗
16. LGBM: A machine learning approach for Ethereum fraud detection
17. Detection of illicit accounts over the Ethereum blockchain10.1016/j.eswa.2020.113318 ↗
18. Evaluation of performance enhancement in Ethereum fraud detection using oversampling techniques10.1016/j.asoc.2024.111698 ↗
19. Dahiya, M., Mishra, N., and Singh, R. (2023;, January 9–11). Neural network based approach for Ethereum fraud detection. Proceedings of the 2023 4th International Conference on Intelligent Engineering and Management (ICIEM), London, UK.10.1109/ICIEM59379.2023.10166745 ↗
20. Transaction-based classification and detection approach for Ethereum smart contract10.1016/j.ipm.2020.102462 ↗
21. Enhanced Anomaly Detection in Ethereum: Unveiling and Classifying Threats with Machine Learning10.1109/ACCESS.2024.3504300 ↗
22. Blockchain-enabled fraud discovery through abnormal smart contract detection on Ethereum10.1016/j.future.2021.08.023 ↗
23. Tan, R., Tan, Q., Zhang, P., and Li, Z. (2021, January 7–8). Graph neural network for ethereum fraud detection. Proceedings of the 2021 IEEE international conference on big knowledge (ICBK), Auckland, New Zealand.10.1109/ICKG52313.2021.00020 ↗
24. Enhancing Ethereum Fraud Detection via Generative and Contrastive Self-supervision10.1109/TIFS.2024.3521611 ↗
25. Ethereum fraud behavior detection based on graph neural networks10.1007/s00607-023-01177-7 ↗
26. Liu, S.Z., Yu, X.Y., Li, Y.T., Zhang, H., Guo, X.P., Ma, C.H., and Long, H.X. (2024). Detection of Ethereum Phishing Fraud Nodes Based on Feature Enhancement Strategy and GBM. Electronics, 13.10.3390/electronics13245060 ↗
27. Dynamic Feature Fusion: Combining Global Graph Structures and Local Semantics for Blockchain Phishing Detection10.1109/TNSM.2025.3576130 ↗
28. LMAE4Eth: Generalizable and Robust Ethereum Fraud Detection by Exploring Transaction Semantics and Masked Graph Embedding10.1109/TIFS.2025.3612149 ↗
29. Li, P., Xie, Y., Xu, X., Zhou, J., and Xuan, Q. (2022, January 4–5). Phishing fraud detection on ethereum using graph neural network. Proceedings of the International Conference on Blockchain and Trustworthy Systems, Chengdu, China.10.1007/978-981-19-8043-5_26 ↗
30. EnLEFD-DM: Ensemble Learning Based Ethereum Fraud Detection Using CRISP-DM Framework10.1111/exsy.13379 ↗
31. Github (2025, May 19). Github Repository Dataset. Available online: https://github.com/fatihertam/ethereumfrauddetection.
32. Explainable AI supported hybrid deep learnig method for layer 2 intrusion detection10.1016/j.eij.2025.100669 ↗
33. Ahn, J.M., Kim, J., and Kim, K. (2023). Ensemble machine learning of gradient boosting (XGBoost, LightGBM, CatBoost) and attention-based CNN-LSTM for harmful algal blooms forecasting. Toxins, 15.10.2139/ssrn.4434784 ↗
34. Chen, T., and Guestrin, C. (2016, January 13–17). Xgboost: A scalable tree boosting system. Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939785 ↗
35. Lightgbm: A highly efficient gradient boosting decision tree
36. CatBoost: Unbiased boosting with categorical features
37. Extracting spatial effects from machine learning model using local interpretation method: An example of SHAP and XGBoost10.1016/j.compenvurbsys.2022.101845 ↗