Scalable Privacy Preservation in Distributed Healthcare AI Models Using Secure Multi-Party Computation and Federated Aggregation
Keywords:
Federated Learning, Secure Multi-Party Computation, Privacy Preservation, Distributed AI, Healthcare Data, Model Aggregation, Secure Aggregation, Differential Privacy, Data Security, Scalable AIAbstract
The rapid digitization of healthcare systems and the integration of AI-driven diagnostics have amplified concerns around patient data privacy. Traditional centralized training of AI models exposes sensitive health records to privacy breaches, prompting the exploration of decentralized, privacy-preserving approaches. This paper proposes a scalable framework that integrates Secure Multi-Party Computation (SMPC) with Federated Learning Aggregation (FLA) to preserve privacy in distributed healthcare AI systems. By evaluating real-world healthcare data across simulated institutions, the framework demonstrates high privacy resilience and model performance without compromising scalability. The proposed solution enables collaborative AI development across healthcare providers while adhering to ethical standards.
References
(1) McMahan, H.B., et al. "Communication-Efficient Learning of Deep Networks from Decentralized Data." Proceedings of AISTATS, vol. 54, 2017.
(2) Brisimi, T.S., et al. "Federated Learning of Predictive Models from Federated Electronic Health Records." Journal of Biomedical Informatics, vol. 87, 2018.
(3) Li, X., et al. "FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare." IEEE Intelligent Systems, vol. 35, no. 4, 2020.
(4) Gundaboina, A. (2025). Endpoint Security for Healthcare Devices: Protecting Patient Data on Windows and Samsung Assets. International Journal of Computer Science and Information Technology Research (IJCSITR), 6(3), 81–100. https://doi.org/10.63530/IJCSITR_2025_06_03_007
(5) Bonawitz, K., et al. "Practical Secure Aggregation for Privacy-Preserving Machine Learning." Proceedings of CCS, vol. 25, 2019.
(6) Hale, T., et al. "Privacy-Preserving Analytics in Healthcare: SMPC in Practice." Health Informatics Journal, vol. 27, no. 3, 2021.
(7) Gundaboina, A. (2025). Zero Trust Architecture for Endpoint Security: Securing Devices in Multi-Platform Environments. World Journal of Advanced Research and Reviews, 26(2), 4531–4543. https://doi.org/10.30574/wjarr.2025.26.2.1672
(8) Shokri, R., and Shmatikov, V. "Privacy-Preserving Deep Learning." Proceedings of CCS, vol. 22, 2015.
(9) Nasr, M., et al. "Comprehensive Privacy Analysis of Federated Learning." IEEE S&P, vol. 39, no. 5, 2020.
(10) Gundaboina, A. (2025). Zero Trust for Multi-Cloud and Hybrid Environments in Healthcare: Protecting Patient Engagement Applications. World Journal of Advanced Research and Reviews, 26(1), 4236–4245. https://doi.org/10.30574/wjarr.2025.26.1.1140
(11) Acar, A., et al. "A Survey on Homomorphic Encryption and Its Applications in Federated Learning." ACM Computing Surveys, vol. 53, no. 6, 2021.
(12) Zhao, Y., et al. "Federated Learning with Non-IID Data." arXiv preprint, vol. 56, 2018.
(13) Hardy, S., et al. "Private Federated Learning on Vertically Partitioned Data via Entity Resolution and Additively Homomorphic Encryption." PoPETs, vol. 2021, no. 4.
(14) Kairouz, P., et al. "Advances and Open Problems in Federated Learning." Foundations and Trends in Machine Learning, vol. 14, no. 1, 2021.
(15) Truex, S., et al. "A Hybrid Approach to Privacy-Preserving Federated Learning." IEEE Transactions on Big Data, vol. 6, no. 3, 2020.
(16) Gundaboina, A.K. (2025). Automated Cloud Security in Healthcare: Ensuring HIPAA Compliance with AI and DevOps. Journal of Artificial Intelligence & Cloud Computing, SRC/JAICC-461. https://doi.org/10.47363/JAICC/2025(4)434
(17) Yin, D., et al. "Gradient Leakage and Protection in Federated Learning." NeurIPS, vol. 33, 2020.
(18) Mohassel, P., and Zhang, Y. "SecureML: A System for Scalable Privacy-Preserving Machine Learning." IEEE S&P, vol. 38, no. 5, 2017.
(19) Geyer, R., et al. "Differentially Private Federated Learning: A Client-Level Perspective." NeurIPS Workshop, vol. 34, 2018.
(20) Gundaboina, A. (2025). Cloud-native encryption for healthcare: Ensuring data privacy in multi-cloud environments. World Journal of Advanced Research and Reviews, 25(1), 2500–2509. https://doi.org/10.30574/wjarr.2025.25.1.0068
Downloads
Published
Issue
Section
Deprecated: urlencode(): Passing null to parameter #1 ($string) of type string is deprecated in /home/u877385332/domains/ijraics.com/public_html/plugins/generic/pflPlugin/PflPlugin.php on line 216
