Skip to main navigation menu Skip to main content Skip to site footer

Vol. 2 No. 1 (2021)
2021 Edition

Articles

AI Models for Real Time Risk Assessment in Decentralized Finance

Published 2021-10-06

  • Rahul Autade

Rahul Autade
Finastra Technologies, USA

Abstract

AI has emerged as the phenomenon set to revolutionize financial services via credit scoring, fraud detection, risk modelling, personalization, etc. But the bigger the need in AI for performance and trust, the bigger the need for massive datasets, diversities, and quality—usually segregated across institutions due to regulatory considerations, privacy issues, or competitiveness. While FL appeared as a privacy-preserving alternative to centralized AI training, classical FL architectures still lacked the notion of trust, auditability, and resilience, especially in such a high-stakes environment as one involving financial institutions.

Keywords

Federated Learning, Blockchain, Secure AI Collaboration, Financial Institutions, Privacy-Preserving AI

View PDF

References

  1. P. Kairouz et al., “Advances and open problems in federated learning,” Foundations and Trends® in Machine Learning, vol. 14, no. 1—2, pp. 1—210, 2021.
  2. Y. Liu et al., “FedFinance: Privacy-preserving federated learning for financial applications,” in Proc. NeurIPS Workshop, 2021.
  3. A. Hard et al., “Federated learning for mobile keyboard prediction,” arXiv preprint arXiv:1811.03604, 2018.
  4. V. Smith et al., “Federated multi-task learning,” in Proc. NIPS, 2017, pp. 4424—4434.
  5. Y. Zhao et al., “Federated learning with non-IID data,” arXiv preprint arXiv:1806.00582, 2018.
  6. D. Froelicher et al., “ChainFL: Secure blockchain-based federated learning,” in Proc. IEEE SPW, 2020, pp. 19—30.
  7. Y. Chen et al., “Achieving traceability in federated learning via blockchain,” Future Generation Computer Systems, vol. 117, pp. 402—413, 2021.
  8. J. Weng et al., “DeepChain: Auditable federated learning via blockchain,” in Proc. IEEE ICDCS, 2021, pp. 133—142.
  9. H. Wang et al., “Blockchain and federated learning for privacy-preserving AI,” IEEE Intelligent Systems, vol. 35, no. 4, pp. 65—71, 2020.
  10. M. Shayan et al., “Biscotti: A blockchain system for private and secure federated learning,” in Proc. USENIX OSDI, 2020, pp. 783—798.
  11. C. Dwork, “Differential privacy,” in Proc. ICALP, 2006, pp. 1—12.
  12. K. Bonawitz et al., “Practical secure aggregation for federated learning on user-held data,” in Proc. NIPS Workshop, 2017.
  13. C. Gentry, “Fully homomorphic encryption using ideal lattices,” in Proc. ACM STOC, 2009, pp. 169—178.
  14. M. Abadi et al., “Deep learning with differential privacy,” in Proc. ACM CCS, 2016, pp. 308—318.
  15. Y. Aono et al., “Privacy-preserving deep learning via additively homomorphic encryption,” IEEE Transactions on Dependable and Secure Computing, vol. 15, no. 5, pp. 725—739, 2018.
  16. N. Szabo, “Formalizing and securing relationships on public networks,” First Monday, vol. 2, no. 9, 1997.
  17. V. Buterin, “A next-generation smart contract and decentralized application platform,” Ethereum White Paper, 2014.
  18. K. Christidis and M. Devetsikiotis, “Blockchains and smart contracts for the Internet of Things,” IEEE Access, vol. 4, pp. 2292—2303, 2016.
  19. B. Liu et al., “Smart contract based governance for federated AI ecosystems,” in Proc. IEEE ISPA, 2021, pp. 389—396.
  20. G. Zyskind, O. Nathan, and A. Pentland, “Decentralizing privacy: Using blockchain to protect personal data,” in Proc. IEEE SPW, 2015, pp. 180—184.
  21. W. Li et al., “Blockchain-based auditing for federated learning,” in Proc. IEEE ICDE, 2020, pp. 1746—1751.
  22. R. Ramakrishnan et al., “Provenance-aware federated learning in multi-institutional medical settings,” arXiv preprint arXiv:2012.11992, 2020.
  23. Doddipatla, L., Ramadugu, R., Yerram, R. R., & Sharma, T. (2021). Exploring The Role of Biometric Authentication in Modern Payment Solutions. International Journal of Digital Innovation, 2(1).
  24. Y. Zhang et al., “Auditable federated learning for medical imaging,” in Proc. MICCAI, 2021, pp. 221—231.
  25. Q. Qu et al., “Blockchain-enabled accountable federated learning for financial risk prediction,” in Proc. IEEE BigData, 2021, pp. 2349—2358.
  26. European Commission, “Proposal for a regulation laying down harmonised rules on artificial intelligence (Artificial Intelligence Act),” Brussels, Apr. 2021.
  27. Basel Committee on Banking Supervision, “Principles for the effective management and supervision of climate-related financial risks,” Bank for International Settlements, 2021.
  28. F. Doshi-Velez and B. Kim, “Towards a rigorous science of interpretable machine learning,” arXiv preprint arXiv:1702.08608, 2017.
  29. M. T. Ribeiro, S. Singh, and C. Guestrin, “Why should I trust you?” in Proc. ACM KDD, 2016, pp. 1135—1144.
  30. A. Shrestha and A. Mahmood, “Review of deep learning algorithms and architectures,” IEEE Access, vol. 7, pp. 53040—53065, 2019.
  31. P. Blanchard et al., “Machine learning with adversaries: Byzantine tolerant gradient descent,” in Proc. NIPS, 2017, pp. 119—129.
  32. C. Fung et al., “Mitigating sybils in federated learning poisoning,” arXiv preprint arXiv:1808.04866, 2018.
  33. R. Ramadugu, L. Doddipatla, and R. R. Yerram, "Risk management in foreign exchange for crossborder payments: Strategies for minimizing exposure," Turkish Online Journal of Qualitative Inquiry, pp. 892-900, 2020.
  34. E. Bagdasaryan et al., “How to backdoor federated learning,” in Proc. AISTATS, 2020, pp. 2938—2948.
  35. D. Yin et al., “Byzantine-robust distributed learning: Towards optimal statistical rates,” in Proc. ICML, 2018, pp. 5650—5659.
  36. Google AI, “Federated learning at scale: Deploying on Android,” 2019. [Online]. Available: https://ai.googleblog.com
  37. IBM Research, “AI governance and risk management for enterprise ML,” 2020. [Online]. Available: https://www.research.ibm.com
  38. OpenMined, “PySyft: Federated learning with privacy-preserving deep learning,” 2021. [Online]. Available: https://www.openmined.org
  39. Microsoft, “SEAL: Microsofts homomorphic encryption library,” 2020. [Online]. Available: https://www.microsoft.com/en-us/research/project/microsoft-seal/
  40. Hyperledger Fabric, “Blockchain for enterprise-grade applications,” Linux Foundation, 2021. [Online]. Available: https://www.hyperledger.org/use/fabric