A Systematic Review on the Application of Artificial Intelligence in Decentralized Finance

Abstract

This study presents a comprehensive systematic review of Artificial Intelligence (AI) applications in Decentralized Finance (DeFi), emphasizing AI’s pivotal role in mitigating the vulnerabilities and operational complexities inherent in permissionless financial systems. By systematically analyzing 39 peer-reviewed studies from major scholarly databases, the review identifies five dominant application domains: fraud detection, smart contract security, market prediction, credit risk assessment, and decentralized governance. It examines the diverse range of AI methods spanning machine learning, deep learning, graph neural networks, and reinforcement learning—and evaluates their comparative performance and limitations. The findings reveal that AI not only enhances DeFi’s transparency, trust, and efficiency but also underpins emerging capabilities such as autonomous governance and adaptive market mechanisms. Persistent challenges including data scarcity, cross-chain generalization, interpretability, and scalability—underscore the need for robust, explainable, and ethical AI solutions. The review concludes that AI constitutes a foundational enabler for secure, transparent, and resilient decentralized financial ecosystems, and outlines critical future research directions for integrating trustworthy intelligence into the evolving DeFi landscape.

References

[1] F. A. Bakare, J. Omojola, and A. C. Iwuh, “Blockchain and decentralized finance (DEFI): Disrupting traditional banking and financial systems,” World Journal of Advanced Research and Reviews, vol. 23, no. 3, pp. 3075–3089, 2024.

[2] P. K. Ozili, “Decentralized finance research and developments around the world,” Journal of Banking and Financial Technology, vol. 6, no. 2,117–133, 2022.

[3] N. Carter and L. Jeng, “DeFi protocol risks: The paradox of DeFi,” Regtech, suptech and beyond: innovation and technology in financial services, riskbooks, forthcoming Q3, 2021.

[4] B. Luo, Z. Zhang, Q. Wang, A. Ke, S. Lu, and B. He, “AI-powered fraud detection in decentralized finance: A project life cycle perspective,” ACM Computing Surveys, vol. 57, no. 4, pp. 1–38, 2024.

[5] S. J. Chavakula, C. A. J. Albert, E. Ebenezer, M. H. Bhagat, and C. V. Mahamuni, “Explainable AI (XAI) Using SHAP and LIME for Financial Fraud Detection and Credit Scoring,” in 2025 International Conference on Advanced Computing Technologies (ICoACT), IEEE, pp. 1–8, 2025.

[6] E. Zmaznev, “Measuring decentralised finance regulatory uncertainty,” Master’s thesis, 2021.

[7] B. Luo, Z. Zhang, Q. Wang, A. Ke, S. Lu, and B. He, “AI-powered fraud detection in decentralized finance: A project life cycle perspective,” ACM Computing Surveys, vol. 57, no. 4, pp. 1–38, 2024.

[8] A. Song, E. Seo, and H. Kim, “Anomaly VAE-transformer: A deep learning approach for anomaly detection in decentralized finance,” IEEE Access, vol. 11, pp. 98115–98131, 2023.

[9] B. Wang, X. Yuan, L. Duan, H. Ma, C. Su, and W. Wang, “DeFiScanner: Spotting DeFi attacks exploiting logic vulnerabilities on blockchain,” IEEE Transactions on Computational Social Systems, vol. 11, no. 2, pp. 1577–1588, 2022.

[10] B. Mazorra, V. Adan, and V. Daza, “Do not rug on me: Leveraging ma- chine learning techniques for automated scam detection,” Mathematics, vol. 10, no. 6, p. 949, 2022.

[11] X. Jiang and W.-T. Tsai, “MVCG-SPS: A Multi-View Contrastive Graph Neural Network for Smart Ponzi Scheme Detection,” Applied Sciences, vol. 15, no. 6, p. 3281, 2025.

[12] Y. Qiao, G. Li, J. Zhou, and W. Wu, “Detecting Rug Pull Scams on Blockchain via Feature Fused Graph Classification,” in CCF China Blockchain Conference, pp. 67–83, Singapore: Springer Nature Singa- pore, 2023.

[13] L. Wang, H. Cheng, Z. Zheng, A. Yang, and M. Xu, “Temporal transaction information-aware Ponzi scheme detection for Ethereum smart contracts,” Engineering Applications of Artificial Intelligence, vol. 126, p. 107022, 2023.

[14] J. Li, F. Baldimtsi, J. P. Brandao, M. Kugler, R. Hulays, E. Showers,Ali, and J. Chang, “Measuring illicit activity in DeFi: The case of Ethereum,” in International Conference on Financial Cryptography and Data Security, pp. 197–203, Berlin, Heidelberg: Springer Berlin Heidelberg, 2021.

[15] V. Mothukuri, R. M. Parizi, J. L. Massa, and A. Yazdinejad, “An AI multi-model approach to DeFi project trust scoring and security,” in 2024 IEEE International Conference on Blockchain (Blockchain), pp. 19–28, IEEE, 2024.

[16] J. Li, G. Lu, Y. Gao, and F. Gao, “A smart contract vulnerability detection method based on multimodal feature fusion and deep learning,” Mathematics, vol. 11, no. 23, p. 4823, 2023.

[17] H. Lakadawala, K. Dzigbede, and Y. Chen, “Detecting reentrancy vulnerability in smart contracts using graph convolution networks,” in 2024 IEEE 21st Consumer Communications & Networking Conference (CCNC), pp. 188–193, IEEE, 2024.

[18] W. Li, X. Li, Y. Zhang, and Z. Li, “Defitail: DeFi protocol inspection through cross-contract execution analysis,” in Companion Proceedings of the ACM Web Conference 2024, pp. 786–789, 2024.

[19] Z. Li, W. Li, X. Li, and Y. Zhang, “Stateguard: Detecting state derail- ment defects in decentralized exchange smart contracts,” in Companion Proceedings of the ACM Web Conference 2024, pp. 810–813, 2024.

[20] X. Liu, G. Wang, M. Chen, P. Li, and J. Zhu, “A vulnerability detec- tion method for smart contracts using opcode sequences with variable length,” in International Conference on Intelligent Computing, pp. 369– 380, Singapore: Springer Nature Singapore, 2024.

[21] M. O. Kotb, “Credit scoring using machine learning algorithms and blockchain technology,” in 2023 Intelligent Methods, Systems, and Applications (IMSA), pp. 381–386, IEEE, 2023.

[22] G. Palaiokrassas, S. Scherrers, E. Makri, and L. Tassiulas, “Machine learning in DeFi: Credit risk assessment and liquidation prediction,” in 2024 IEEE International Conference on Blockchain and Cryptocurrency (ICBC), pp. 650–654, IEEE, 2024.

[23] L. Ramachandran, S. Shanthana, A. Gokulakrishnan, S. Kumar, K. S. Vishal, and G. Sahaana, “Decentralized financial stocks prediction using deep regression learning,” in 2024 2nd International Conference on Disruptive Technologies (ICDT), pp. 1298–1302, IEEE, 2024.

[24] T. Lim, “Predictive crypto-asset automated market making architecture for decentralized finance using deep reinforcement learning,” arXiv preprint arXiv:2211.01346, 2022.

[25] V. Nadkarni, J. Hu, R. Rana, C. Jin, S. Kulkarni, and P. Viswanath, “Ze- roSwap: Data-driven optimal market making in decentralized finance,” in International Conference on Financial Cryptography and Data Security,209–227, Cham: Springer Nature Switzerland, 2024.

[26] D. Churiwala and B. Krishnamachari, “Qlammp: A Q-learning agent for optimizing fees on automated market making protocols,” in 2023 Fifth International Conference on Blockchain Computing and Applications (BCCA), pp. 274–281, IEEE, 2023.

[27] R. Jagdale and M. Deshmukh, “Natural language processing in finance: Techniques, applications, and future directions,” in Machine Learning and Modeling Techniques in Financial Data Science, pp. 411–434, IGI Global Scientific Publishing, 2025.

[28] I. Ghosh, E. Alfaro-Corte´s, M. Ga´mez, and N. Garc´ıa-Rubio, “Prediction and interpretation of daily NFT and DeFi prices dynamics: Inspection through ensemble machine learning & XAI,” International Review of Financial Analysis, vol. 87, 2023, article 102558.

[29] B. B. Gupta, A. Gaurav, J. Pin˜eiro-Chousa, M. A´ . Lo´pez-Cabarcos, and I. Gonza´lez Lo´pez, “Predicting the variation of decentralised finance cryptocurrency prices using deep learning and a BiLSTM-LSTM based approach,” Enterprise Information Systems, 2025, article 2483456.

[30] S. Sruthi and D. Saravanan, “Forecasting cryptocurrency prices in the DeFi ecosystem using predictive models,” in 2025 International Conference on Computing for Sustainability and Intelligent Future (COMP-SIF), pp. 1–6, IEEE, 2025.

[31] L. Mussoi Almeida, F. M. Mu¨ller, and M. S. Perlin, “Risk forecasting comparisons in decentralized finance: An approach in constant product market makers,” Computational Economics, vol. 65, no. 1, pp. 395–428, 2025.

[32] J. Xu, Y. Feng, D. Perez, and B. Livshits, “Auto. gov: Learning-based governance for decentralized finance (DeFi),” IEEE Transactions on Services Computing, 2025.

[33] V. M. Ngo, P. V. Nguyen, H. H. Nguyen, H. X. T. Tram, and L. C. Hoang, “Governance and monetary policy impacts on public acceptance of CBDC adoption,” Research in International Business and Finance, vol. 64, 2023, article 101865.

[34] S. V. Jin, ““Technopian but lonely investors?”: Comparison between investors and non-investors of blockchain technologies, cryptocurrencies, and non-fungible tokens (NFTs) in artificial intelligence-driven FinTech and decentralized finance (DeFi),” Telematics and Informatics Reports, vol. 14, 2024, article 100128.

[35] S. Agal, K. M. Raulji, Y. Farooqui, N. Bhavsar, and R. Agrawal, “Innovative financial services driven by AI and blockchain synergy for decentralized trust and personalized solutions,” in 2024 Eighth International Conference on Parallel, Distributed and Grid Computing (PDGC), pp. 363–370, IEEE, 2024.

[36] S. Fan, N. Ilk, A. Kumar, R. Xu, and J. L. Zhao, “Blockchain as a trust machine: From disillusionment to enlightenment in the era of generative AI,” Decision Support Systems, vol. 182, 2024, article 114251.

[37] A. Geimer, B. Fiz, and R. State, “WallStreetFeds: Client-specific tokens as investment vehicles in federated learning,” in Proceedings of the 5th ACM International Conference on AI in Finance, pp. 839–846, 2024.

[38] P. Xia, H. Wang, B. Gao, W. Su, Z. Yu, X. Luo, C. Zhang, X. Xiao, and G. Xu, “Trade or trick? Detecting and characterizing scam tokens on Uniswap decentralized exchange,” Proceedings of the ACM on Measurement and Analysis of Computing Systems, vol. 5, no. 3, pp. 1–26, 2021.

[39] M. K. Hassan, F. A. Hudaefi, and R. E. Caraka, “Mining netizen’s opinion on cryptocurrency: Sentiment analysis of Twitter data,” Studies in Economics and Finance, vol. 39, no. 3, pp. 365–385, 2022.

[40] R. Thatikonda, J. Ponnala, D. K. Yendluri, M. Kempanna, R. Tatikonda, and A. Bhuvanesh, “The impact of blockchain and AI in the finance industry,” in 2023 International Conference on Computational Intelli- gence, Networks and Security (ICCINS), pp. 1–6, IEEE, 2023.

[41] M. Gunathilaka, S. Wickramanayake, and H. M. N. Dilum Bandara, “DeFiTrust: A transformer-based framework for scam DeFi token de- tection using event logs and sentiment analysis,” Expert Systems with Applications, vol. 251, 2024, article 123913.

[42] S. El Haddouti, M. Khaldoune, M. Ayache, and M. D. E. K. El Kettani, “Smart contracts auditing and multi-classification using machine learning algorithms: An efficient vulnerability detection in Ethereum blockchain,” Computing, vol. 106, no. 9, pp. 2971–3003, 2024.

[43] A. Trozze, B. Kleinberg, and T. Davies, “Detecting DeFi securities violations from token smart contract code,” Financial Innovation, vol. 10, no. 1, pp. 1–35, 2024.

[44] T. Igarashi and K. Matsuura, “Scam token detection based on static analysis before contract deployment,” in International Conference on Fi- nancial Cryptography and Data Security, pp. 189–206, Cham: Springer Nature Switzerland, 2024.

[45] G. Palaiokrassas, S. Scherrers, I. Ofeidis, and L. Tassiulas, “Leveraging machine learning for multichain DeFi fraud detection,” in 2024 IEEE International Conference on Blockchain and Cryptocurrency (ICBC),678–680, IEEE, 2024.

[46] M. Hafeez and Z. A. Uzmi, “Unveiling market dynamics and strategic interactions in crypto arbitrage,” in 2024 6th International Conference on Blockchain Computing and Applications (BCCA), pp. 617–623, IEEE, 2024.

[47] Mohammadagha M. Hyperparameter Optimization Strategies for Tree-Based Machine Learning Models Prediction: A Comparative Study of AdaBoost, Decision Trees, and Random Forest. Decision Trees, and Random Forest (April 11, 2025). 2025 Apr 11.

[48] Mohammadagha M, Najafi M, Kaushal V, Jibreen AM. Machine learning models for reinforced concrete pipes condition prediction: The state-of-the-art using artificial neural networks and multiple linear regression in a Wisconsin case study. arXiv preprint arXiv:2502.00363. 2025 Feb 1.

[49] Ataei S, Ataei ST, Saghiri AM. Applications of Deep Learning to Cryptocurrency Trading: A Systematic Analysis