International Journal of P2P
Network Trends and Technology

Research Article | Open Access | Download PDF
Volume 16 | Issue 2 | Year 2026 | Article Id. IJPTT-V16I2P401 | DOI : https://doi.org/10.14445/22492615/IJPTT-V16I2P401

PRISM-NRL: A Privacy-Preserving Regret-Minimising Intelligent System for Medical IoT Using No-Regret Learning and Differential Privacy

Manas Kumar Yogi, B. Kalyan Chakravarthy

Received Revised Accepted Published
16 Jun 2026 27 Jul 2026 12 Aug 2026 29 Aug 2026

Citation :

Manas Kumar Yogi, B. Kalyan Chakravarthy, "PRISM-NRL: A Privacy-Preserving Regret-Minimising Intelligent System for Medical IoT Using No-Regret Learning and Differential Privacy," International Journal of P2P Network Trends and Technology (IJPTT), vol. 16, no. 2, pp. 1-12, 2026. Crossref, https://doi.org/10.14445/22492615/IJPTT-V16I2P401

Abstract

Medical IoT (MIoT) environments create continuous flows of patient information with high privacy exposure risks, both clinically and in terms of regulatory compliance. Current approaches like standard differential privacy and local differential privacy either over-perturb data, making it less clinically useful or cannot dynamically respond to adversarially varying loss landscapes. The paper introduces PRISM-NRL (Privacy-preserving Regret-minimizing Intelligent System for Medical IoT via No-Regret Learning), a framework based on game theory, where privacy policy selection is modeled as a repeated game between the learner and the adversarial environment. PRISM-NRL combines the Follow-The-Leader (FTL) strategy with an adaptive Hedge algorithm and calibrated Laplace differential privacy noise to guarantee an average regret of O(√(ln N / T)) with an ε-differential privacy guarantee. When tested on MIMIC-III, eICU-CRD, PhysioNet-2012 and PTB-XL benchmarks, PRISM-NRL improves privacy loss by up to 15.2 percentage points, and it outperforms all baselines with an F1-score of 0.93 and an AUC-ROC of 0.96.

Keywords

Cyber - Physical Systems, Differential Privacy, Follow-The-Leader, Game Theory, Mimic-Iii, Medical Iot, No-Regret Learning, Privacy Preservation.

References

[1] Martin Abadi et al., “Deep Learning with Differential Privacy,” Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, Association for Computing Machinery, New York, NY, United States, pp. 308-318, 2016.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Mohammed Ali Al-Garadi et al., “A Survey of Machine and Deep Learning Methods for Internet of Things (IoT) Security,” IEEE Communications Surveys & Tutorials, vol. 22, no. 3, pp. 1646-1685, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Ioannis Anagnostides et al., “Near-Optimal No-Regret Learning for Correlated Equilibria in Multi-Player General-Sum Games,” Proceedings of the 54th Annual ACM SIGACT Symposium on Theory of Computing, Association for Computing Machinery, New York, NY, United States, pp. 736-749, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Pathum Chamikara Mahawaga Arachchige et al., “Local Differential Privacy for Deep Learning,” IEEE Internet of Things Journal, vol. 7, no. 7, pp. 5827-5842, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Maria-Florina Balcan, Avrim Blum, and Santosh Vempala, “Efficient Representations for Lifelong Learning and Autoencoding,” Proceedings of the 28th Conference on Learning Theory, pp. 1-20, 2022.
[Google Scholar] [Publisher Link]

[6] Keith Bonawitz et al., “Practical Secure Aggregation for Privacy-Preserving Machine Learning,” Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, pp. 1175-1191, 2017.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Kamalika Chaudhuri, Claire Monteleoni, and Anand D. Sarwate, “Differentially Private Empirical Risk Minimization,” Journal of Machine Learning Research, vol. 12, no. 3, pp. 1069-1109, 2011.
[Google Scholar] [Publisher Link]

[8] John C. Duchi, Michael I. Jordan, and Martin J. Wainwright, “Local Privacy and Statistical Minimax Rates,” 2013 IEEE 54th Annual Symposium on Foundations of Computer Science, Berkeley, CA, USA, pp. 429-438, 2013.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Cynthia Dwork, and Aaron Roth, “The Algorithmic Foundations of Differential Privacy,” Foundations and Trends in Theoretical Computer Science, vol. 9, no. 3-4, pp. 211-487, 2014.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Minghong Fang et al., “Local Model Poisoning Attacks to Byzantine-Robust Federated Learning,” 29th USENIX Security Symposium. USENIX Association, pp. 1-18, 2020.
[Google Scholar] [Publisher Link]

[11] Robin C. Geyer, Tassilo Klein, and Moin Nabi, “Differentially Private Federated Learning: A Client Level Perspective,” arXiv preprint, pp. 1-7, 2017.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Andrew Hard et al., “Federated Learning for Mobile Keyboard Prediction,” arXiv preprint, pp. 1-7, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Hongsheng Hu et al., “Membership Inference Attacks on Machine Learning: A Survey,” arXiv preprint, pp. 1-37, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Alistair E.W. Johnson et al., “MIMIC-III, A Freely Accessible Critical Care Database,” Scientific Data, vol. 3, no. 1, pp. 1-9, 2016.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Shiva Prasad Kasiviswanathan et al., “What Can We Learn Privately?,” SIAM Journal on Computing, vol. 40, no. 3, pp. 793-826, 2011.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Mikhail Khodak, Maria-Florina Balcan, and Ameet S. Talwalkar, “Adaptive Gradient-based Meta-Learning Methods,” Advances in Neural Information Processing Systems, vol. 32, 2019.
[Google Scholar] [Publisher Link]

[17] Tian Li et al., “Federated Learning: Challenges, Methods, and Future Directions,” IEEE Signal Processing Magazine, vol. 37, no. 3, pp. 50-60, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Ximeng Liu et al., “Privacy-Preserving Patient-Centric Clinical Decision Support System on Naïve Bayesian Classification,” IEEE Journal of Biomedical and Health Informatics, vol. 20, no. 2, pp. 655-668, 2015.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Lingjuan Lyu, Han Yu, and Qiang Yang, “Threats to Federated Learning: A Survey,” arXiv preprint, pp. 1-7, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Mohammad Ali Maddah-Ali, and Ulrich Niesen, “Fundamental Limits of Caching,” IEEE Transactions on Information Theory, vol. 60, no. 5, pp. 2856-2867, 2014.
[CrossRef] [Google Scholar] [Publisher Link]

[21] Brendan McMahan et al., “Communication-Efficient Learning of Deep Networks from Decentralized Data,” Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, vol. 54, pp. 1273-1282, 2017.
[Google Scholar] [Publisher Link]

[22] Luca Melis et al. “Exploiting Unintended Feature Leakage in Collaborative Learning,” 2019 IEEE Symposium on Security and Privacy, San Francisco, CA, USA, pp. 691-706, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[23] Ilya Mironov, “Rényi Differential Privacy,” 2017 IEEE 30th Computer Security Foundations Symposium (CSF), Santa Barbara, CA, USA, pp. 263-275, 2017.
[CrossRef] [Google Scholar] [Publisher Link]

[24] Noman Mohammed et al., “Privacy-Preserving Heterogeneous Health Data Sharing,” Journal of the American Medical Informatics Association, vol. 20, no. 3, pp. 462-469, 2013.
[CrossRef] [Google Scholar] [Publisher Link]

[25] Payman Mohassel, and Yupeng Zhang, “SecureML: A System for Scalable Privacy-Preserving Machine Learning,” 2017 IEEE Symposium on Security and Privacy (SP), San Jose, CA, USA, pp. 19-38, 2017.
[CrossRef] [Google Scholar] [Publisher Link]

[26] Travis B. Murdoch, and Allan S. Detsky, “The Inevitable Application of Big Data to Health Care,” JAMA, vol. 309, no. 13, pp. 1351-1352, 2013.
[CrossRef] [Google Scholar] [Publisher Link]

[27] Milad Nasr, Reza Shokri, and Amir Houmansadr, “Machine Learning with Membership Privacy using Adversarial Regularization,” Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security, pp. 634-646, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[28] Ahmed El Ouadrhiri, and Ahmed Abdelhadi, “Differential Privacy for Deep and Federated Learning: A Survey,” IEEE Access, vol. 10, pp. 22359-22380, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[29] Athanasios S. Polydoros, and Lazaros Nalpantidis, “Survey of Model-Based Reinforcement Learning: Applications on Robotics,” Journal of Intelligent & Robotic Systems, vol. 86, no. 2, pp. 153-173, 2017.
[CrossRef] [Google Scholar] [Publisher Link]

[30] Pranav Rajpurkar et al., “CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning,” arXiv preprint, pp. 1-7, 2017.
[CrossRef] [Google Scholar] [Publisher Link]

[31] Jean Louis Raisaro et al., “SCOR: A Secure International Informatics Infrastructure to Investigate COVID-19,” Journal of the American Medical Informatics Association, vol. 27, no. 11, pp. 1721-1726, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[32] Jordi Soria-Comas, and Josep Domingo-Ferrer, “Big Data Privacy: Challenges to Privacy Principles and Models,” Data Science and Engineering, vol. 1, no. 1, pp. 21-28, 2016.
[CrossRef] [Google Scholar] [Publisher Link]

[33] Stacey Truex et al., “A Hybrid Approach to Privacy-Preserving Federated Learning,” Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security, pp. 1-11, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[34] Patrick Wagner et al., “PTB-XL, a Large Publicly Available Electrocardiography Dataset,” Scientific Data, vol. 7, no. 1, pp. 1-15, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[35] Qiang Yang et al., “Federated Machine Learning: Concept and Applications,” ACM Transactions on Intelligent Systems and Technology, vol. 10, no. 2, pp. 1-19, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[36] Yue Zhao et al., “Federated Learning with Non-IID Data,” arXiv preprint, pp. 1-12, 2018.
[CrossRef] [Google Scholar] [Publisher Link]