Mathematical foundations of secure AI : Homomorphic encryption for distributed learning systems

Babbar, Nandini; Sharma, Amit Kumar; Saini, Ravindra Kumar; Verma, Neeraj Kumar

doi:10.47974/JDMSC-2441

Open Access Research Article

Mathematical foundations of secure AI : Homomorphic encryption for distributed learning systems

Nandini Babbarnandini.babbar@jaipur.manipal.eduDepartment of IoT and Intelligent Systems Manipal University JaipurJaipur, Rajasthan, 303007, IndiaView full profile → , ^*Amit Kumar SharmaCorresponding authoramit.sharma@jaipur.manipal.eduDepartment of Computer and Communication Engineering Manipal University JaipurJaipur, Rajasthan, 303007, IndiaView full profile → , Ravindra Kumar Sainiravindra.saini@jaipur.manipal.eduDepartment of Information Technology Manipal University JaipurDepartment of Information Technology Manipal University JaipurJaipur, Rajasthan, 303007, IndiaView full profile → , Neeraj Kumar Vermaneeraj.verma@jaipur.manipal.eduDepartment of Data Science Manipal University JaipurDepartment of Data Science and Engineering Manipal University JaipurJaipur, Rajasthan, 303007, IndiaView full profile →

* Corresponding author · click or hover a name for details

pp. 2967–2975Vol. 28Issue 8December 2025DOI: 10.47974/JDMSC-2441 Crossmark XML

Received:: 07 Jan 2025
Published Online:: 08 Dec 2025
Article type:: Research Article
Language:: EN
Article no.:: JDMSC-2441
Pages:: 2967–2975

Abstract

Issues concerning the safety and privacy of facts are heightened with the upward push of new disbursed studying structures like federated getting to know. the extent of computation accomplished on encrypted information would require specific encryption, otherwise referred to as homomorphic encryption (HE) defends towards data decryption dangers. this article investigates how the arithmetic of HE lets in its application inside remote studying architectures. This examination carries superior modular mathematics structures, lattice frameworks, and polynomial encoding at the side of traditional framework HE systems. also, the paintings propose a relaxed structure for dispensed mastering that makes use of HE for version aggregation and personal gradient computation. Sectors forced below strict facts secrecy policies like in non-public healthcare, smart towns, and finance illustrate why those rules enforced look coverage freedom capitalism - why even more is wanted. This look at highlights the particular approaches HE can serve as a policy flexed surveillance capitalism- coverage that will become so much extra surveillance-centric to defend something in covered AI structures, therefore laying a coverage for research directed towards AI that prioritizes person privateness.

Keywords

Homomorphic encryption Federated learning security Encrypted computation Lattice-based cryptography

Subject Classifications

68T0568T0768W1594A60

References

[1] S. X., “Federated learning in edge computing environments: Opportunities, challenges, and future directions,” International Journal of Science and Research (IJSR), vol. 13, no. 9, pp. 275–278 (Sep. 2024), doi: 10.21275/es24903163414.
[2] A. Acar, H. Aksu, A. S. Uluagac, and M. Conti, “A survey on homomorphic encryption schemes,” ACM Computing Surveys, vol. 51, no. 4, pp. 1–35 (Sep. 2018), doi: 10.1145/3214303.
[3] J. Li and H. Huang, “Faster secure data mining via distributed homomorphic encryption,” in Proc. 26th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining (KDD ’20), pp. 2706–2714 (Aug. 2020), doi: 10.1145/3394486.3403321.
[4] H. Fang and Q. Qian, “Privacy-preserving machine learning with homomorphic encryption and federated learning,” Future Internet, vol. 13, no. 4, pp. 94 (Apr. 2021), doi: 10.3390/fi13040094.
[5] A. J. Obaid, “Cutting-edge cryptography and cybersecurity: Innovations and applications,” Journal of Discrete Mathematical Sciences and Cryptography, vol. 27, no. 5, pp. i–vii (2024), doi: 10.47974/JDMSC-27-5-foreword.
[6] Y. Shoukry, K. Gatsis, A. Alanwar, G. J. Pappas, S. A. Seshia, M. Srivastava, and P. Tabuada, “Privacy-aware quadratic optimization using partially homomorphic encryption,” Oxford University Research Archive (ORA), Univ. of Oxford (Dec. 2016), doi: 10.1109/CDC.2016.7799042.
[7] V. D. Gowda, V. Praveena, M. Nagabhushanam, P. S. Kumar, C. Rafael, and D. Pathak, “Homomorphic encryption performance in secure data processing for machine learning,” Journal of Discrete Mathematical Sciences and Cryptography, vol. 28, no. 5-A, pp. 1517–1526 (Jan. 2025), doi: 10.47974/JDMSC-2150.
[8] U. Upadhyay, A. Kumar, S. Roy, and U. Rawat, “Balancing innovation and privacy: A machine learning perspective,” Journal of Discrete Mathematical Sciences and Cryptography, vol. 27, no. 2-B, pp. 547–557 (2024), doi: 10.47974/JDMSC-1877.
[9] C. Ma, J. Li, K. Wei, B. Liu, M. Ding, L. Yuan, Z. Han, and H. V. Poor, “Trusted AI in multiagent systems: An overview of privacy and security for distributed learning,” Proceedings of the IEEE, vol. 111, no. 9, pp. 1097–1132 (Sep. 2023), doi: 10.1109/JPROC.2023.3306773.
[10] S. Sheela, S. Jyothi, S. Shalini, and L. Anuj, “Federated learning and deep learning-driven adaptive cryptography for context-aware elliptic curve Diffie–Hellman optimization and anomaly-aware key management in next-generation wireless networks,” Journal of Discrete Mathematical Sciences and Cryptography, vol. 28, no. 5-B, pp. 2151–2161 (Jan. 2025), doi: 10.47974/JDMSC-2431.
[11] Muskan and S. S. Chauhan, “A theoretical approach to find the solution of population-based mathematical model,” Journal of Interdisciplinary Mathematics, vol. 27, no. 8, pp. 1735–1740 (Jan. 2024), doi: 10.47974/JIM-2035.
[12] S. Truex, N. Baracaldo, A. Anwar, T. Steinke, H. Ludwig, R. Zhang, and Y. Zhou, “A hybrid approach to privacy-preserving federated learning,” in Proc. 12th ACM Workshop on Artificial Intelligence and Security (AISec ’19) (2019), doi: 10.1145/3338501.3357370.
[13] Alavi, Maryam, George M. Marakas, and Youngjin Yoo. “A comparative study of distributed learning environments on learning outcomes.” Information Systems Research, vol. 13, no. 4 (2002): 404-415, doi: https://doi.org/10.1287/isre.13.4.404.72.

Views: 74Downloads: 7Citations: 0