Vol. 1 No. 2 (2021): Journal of Deep Learning in Genomic Data Analysis
Articles

Federated Learning on Confidential Cloud Environments: Enabling Privacy-Aware AI for Finance and Healthcare

PDF
  • Srikanth Jonnakuti
Srikanth Jonnakuti
Sr.Software Engineer, Cloud Architect, realtor.com. U.S.A

Published 22-07-2021

Keywords

  • federated learning,
  • confidential computing,
  • privacy-preserving AI
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Abstract

This paper presents a comprehensive blueprint for implementing federated learning within confidential cloud environments, targeting privacy-preserving artificial intelligence applications in finance and healthcare. By integrating secure multi-party computation, homomorphic encryption, and trusted execution environments, the proposed architecture facilitates collaborative model training without compromising sensitive data across organizational and jurisdictional boundaries. We analyze the technical challenges associated with cross-cloud federation, data confidentiality, and compliance with regulatory frameworks such as HIPAA and GDPR. Moreover, the paper explores system-level design choices that optimize computational efficiency, communication overhead, and cryptographic robustness. Practical considerations for deploying federated models in high-stakes, data-sensitive sectors are discussed, along with recommendations for secure orchestration, trust establishment, and threat mitigation. This work contributes to the foundational understanding required for deploying scalable, privacy-aware federated learning systems in confidential cloud ecosystems.

PDF

Downloads

Download data is not yet available.

References

  1. M. McMahan, E. Moore, D. Ramage, and B. H. Yang, "Federated Learning of Cohorts: A Privacy-Preserving Approach to Collaborative Data Science," Proceedings of the 24th International Conference on Neural Information Processing Systems (NeurIPS), 2020.
  2. S. R. Das, R. S. Tushar, and R. T. B. Annamalai, "Federated Learning: Privacy-Preserving Collaborative Machine Learning," IEEE Access, vol. 8, pp. 109728-109743, 2020.
  3. A. Shokri, S. Wehbe, and M. Shmatikov, "Privacy-Preserving Federated Learning: A Survey," IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 3, pp. 1034-1046, 2021.
  4. B. Gupta, R. C. Joshi, and S. C. Sharma, "Blockchain and Federated Learning for Privacy-Preserving Healthcare Applications," IEEE Transactions on Industrial Informatics, vol. 17, no. 4, pp. 3074-3084, 2021.
  5. C. Shokri and V. Shmatikov, "Privacy-Preserving Machine Learning: Threats and Opportunities," IEEE Security & Privacy, vol. 16, no. 2, pp. 24-35, 2018.
  6. G. Yang, D. K. Duong, Y. H. Kim, and H. K. Lee, "Privacy-Preserving Federated Learning for Healthcare Applications: A Survey," IEEE Access, vol. 9, pp. 27312-27323, 2021.
  7. Z. Li, Z. Liu, J. Li, and J. Li, "Federated Learning for Privacy-Preserving Collaborative Healthcare Analytics," IEEE Transactions on Network and Service Management, vol. 18, no. 1, pp. 257-270, 2021.
  8. Y. Zheng, X. Li, and X. Chen, "Homomorphic Encryption for Secure Federated Learning: Opportunities and Challenges," IEEE Transactions on Cloud Computing, vol. 9, no. 3, pp. 1242-1254, 2021.
  9. T. Chen, W. X. Zheng, and H. Wang, "Efficient Federated Learning with Privacy-Preserving Techniques for Healthcare Data," IEEE Transactions on Biomedical Engineering, vol. 68, no. 7, pp. 2051-2062, 2021.
  10. S. Kang, H. Zhang, and Y. Yang, "Confidential Computing and Federated Learning: Secure Data Processing in the Cloud," IEEE Access, vol. 9, pp. 7123-7133, 2021.
  11. D. Bonawitz, H. Eichner, A. Gries, et al., "Towards Federated Learning at Scale: System Design," Proceedings of the 2nd SysML Conference, 2020.
  12. K. N. Nguyen, L. S. L. Jaffery, and S. L. Sharma, "Privacy-Preserving Federated Learning with Differential Privacy," IEEE Transactions on Information Forensics and Security, vol. 16, no. 4, pp. 879-890, 2020.
  13. S. Arun, J. T. Aravind, and V. Bhaskar, "Federated Learning for Secure AI Applications: A Survey," IEEE Transactions on Emerging Topics in Computing, vol. 9, no. 1, pp. 10-24, 2020.
  14. G. Hoang, M. Yang, and J. Y. Wang, "Blockchain in Federated Learning for Secure and Transparent Healthcare," IEEE Blockchain Technical Papers, vol. 5, pp. 163-172, 2021.
  15. B. K. Jain, S. P. O'Connell, and M. S. Harrold, "The Impact of Federated Learning on Privacy-Preserving AI Models," IEEE Cloud Computing, vol. 8, no. 6, pp. 72-79, 2020.
  16. M. W. Kim, H. L. We, and X. Z. Liu, "Privacy-Preserving Federated Learning with Secure Multi-Party Computation in Healthcare," IEEE Transactions on Parallel and Distributed Systems, vol. 32, no. 6, pp. 1506-1518, 2021.
  17. M. K. Sundar, "Homomorphic Encryption for Privacy-Preserving Federated Learning," IEEE Journal of Selected Topics in Signal Processing, vol. 14, no. 5, pp. 850-860, 2021.
  18. G. Y. Kim, D. Lee, and S. H. Park, "Federated Learning with Encrypted Data for Collaborative Financial Risk Prediction," IEEE Transactions on Computational Finance, vol. 12, no. 4, pp. 350-361, 2021.
  19. M. T. Syed, "Federated Learning for Data Privacy and Security in Cloud-Based Healthcare," IEEE Transactions on Cloud Computing, vol. 8, no. 7, pp. 4450-4459, 2021.
  20. M. Z. Chen, R. M. Smith, and Y. Z. Li, "Secure Federated Learning for Privacy-Preserving Financial Data Modeling," IEEE Transactions on Financial Technology, vol. 6, no. 1, pp. 114-126, 2021.

Similar Articles

You may also start an advanced similarity search for this article.