Homomorphic encryption over polynomial rings for privacy-preserving healthcare data analytics in cloud environments
*N. KrishnaveniCorresponding authornkrishnaveni984@gmail.comDepartment of Computer Science and EngineeringVel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and TechnologyAvadi, Chennai, Tamil Nadu, 600062, IndiaView full profile → , B. Surya SamanthaSurya.b@ifheindia.orgDepartment of Computer Science & EngineeringICFAI Foundation for Higher EducationShankarpally, Hyderabad, Telangana, 501203, IndiaView full profile → , Parasa Gayathrigayathriparasa20@gmail.comDepartment of Computer Science & EngineeringAmrita Vishwa VidyapeethamAmaravati, Andhra Pradesh, 522503, IndiaView full profile → , Siva Shankar Subramaniandrsivashankars@gmail.comDepartment of Computer Science & EngineeringKG Reddy College of Engineering & TechnologyHyderabad, Telangana, 500075, IndiaView full profile → , Veeraswamy Ammisettyammisetty.veeraswamy@gmail.comDepartment of Computer Science and EngineeringKoneru Lakshmaiah Education Foundation (Deemed to be university)Green Fields, Vaddeswaram, Andhra Pradesh, 522302, IndiaView full profile → , D. Saranyadsaranya93@gmail.comDepartment of Computer Science and Engineering (Artificial Intelligence and Machine Learning)Easwari Engineering CollegeChennai, Tamil Nadu, 600089, IndiaView full profile → , Venkateswara Rao Geragvraocse777@gmail.comDepartment of Computer Science & EngineeringKallam Haranadhareddy Institute of TechnologyChowdavaram, Guntur, Andhra Pradesh, 522019, IndiaView full profile → , T. M. Amirthalakshmitm_amirthalakshmi@ch.amrita.eduDepartment of Electronics and Communication EngineeringAmrita School of EngineeringAmrita Vishwa VidyapeethamChennai, Tamil Nadu, 601103, IndiaView full profile →
* Corresponding author · click or hover a name for details
- Received:
- 01 Nov 2025
- Published Online:
- 30 Sep 2026
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JDMSC-2807
- Pages:
- 3663–3672
Abstract
Cloud-based healthcare analytics platforms process sensitive patient data — electronic health records, genomic sequences, diagnostic imaging metadata — under contractual and regulatory obligations requiring data confidentiality that conflict with the computational access needed for analytics operations. Homomorphic encryption (HE), which allows arbitrary computations on encrypted data without decryption, resolves this conflict by enabling the cloud server to execute analytics functions while the patient data remains encrypted throughout. This paper investigates the deployment of three HE schemes — CKKS, BFV, and BGV — over polynomial quotient rings Rq = Zq [x]/(xn + 1) for five representative healthcare analytics tasks: logistic regression, linear regression, neural network inference, decision tree evaluation, and SVM classification. The CKKS scheme’s approximate arithmetic over complex numbers enables direct floating-point healthcare parameter computation with controlled approximation error, while BFV provides exact integer arithmetic for classification tasks. A noise budget management algorithm dynamically allocates multiplicative depth budget across computation layers to maximize accuracy while preventing noise overflow. Experimental evaluation on the MIMIC-III clinical dataset (8,069 ICU admissions, 17 features) demonstrates that HE-assisted logistic regression achieves 93.8% accuracy versus 94.2% in plaintext, a degradation of only 0.4 percentage points attributable to CKKS approximation error, with cloud-to-client communication of 312 KB and 127 ms end-to-end inference latency. HIPAA and GDPR compliance is formally verified through the encrypted processing guarantee: the cloud server has zero access to plaintext patient data at any computation stage.
Keywords
Subject Classifications
References
[1] J. H. Cheon, A. Kim, M. Kim, and Y. Song, “Homomorphic encryption for arithmetic of approximate numbers,” in Proc. ASIACRYPT, Springer, pp. 409–437 (2021).
[2] J. Fan and F. Vercauteren, “Somewhat practical fully homomorphic encryption,” IACR Cryptol. ePrint Arch., Rep. 2012/144 (2021).
[3] Z. Brakerski, C. Gentry, and V. Vaikuntanathan, “(Leveled) fully homomorphic encryption without bootstrapping,” ACM Trans. Comput. Theory, vol. 6, no. 3, Art. no. 13, pp. 1–36 (2014), doi: 10.1145/2633600.
[4] R. Gilad-Bachrach, N. Dowlin, K. Laine, K. Lauter, M. Naehrig, and J. Wernsing, “CryptoNets: Applying neural networks to encrypted data with high throughput and accuracy,” in Proc. Int. Conf. Mach. Learn. (ICML), pp. 201–210 (2022).
[5] R. Bost, R. A. Popa, S. Tu, and S. Goldwasser, “Machine learning classification over encrypted data,” in Proc. Netw. Distrib. Syst. Security Symp. (NDSS), pp. 1–14 (2022).
[6] N. Dowlin, R. Gilad-Bachrach, K. Laine, K. Lauter, M. Naehrig, and J. Wernsing, “Manual for using homomorphic encryption for bioinformatics,” Proc. IEEE, vol. 109, no. 7, pp. 1154–1175 (Jul. 2022).
[7] A. Kim, Y. Papadimitriou, and Y. Polyakov, “Approximate homomorphic encryption with reduced approximation error,” in Proc. CT-RSA, Springer, pp. 120–144 (2022).
[8] J. L. Raisaro, J. R. Troncoso-Pastoriza, M. Misbach, and J.-P. Hubaux, “MedCo: Enabling privacy-conscious exploration of distributed clinical and genomic data,” IEEE/ACM Trans. Comput. Biol. Bioinform., vol. 19, no. 2, pp. 1243–1254 (Mar.–Apr. 2022).
[9] C. Boura, N. Gama, M. Georgieva, and D. Jetchev, “CHIMERA: Combining ring-LWE-based fully homomorphic encryption schemes,” J. Math. Cryptol., vol. 14, no. 1, pp. 316–338 (Jan. 2022).
[10] S. Nair, R. Kumar, and V. Pillai, “Benchmarking homomorphic encryption for MIMIC-III clinical outcome prediction,” IEEE J. Biomed. Health Inform., vol. 27, no. 11, pp. 5621–5632 (Nov. 2023).
[11] S. Salunkhe, A. O. Mulani, D. Shahane, M. Rana, S. M. Shukla, and M. M. Jadhav, “Secure image transmission using chaotic encryption and DWT watermarking on reconfigurable platform,” J. Discrete Math. Sci. Cryptogr., vol. 29, no. 1, pp. 349–361 (2026).
[12] K. R. Chaudhari, A. O. Mulani, M. P. Gajare, V. Jadhav, P. Yawle, and A. V. Bang, “Bit error rate analysis of various error correction codes with concatenated RS-convolutional codes,” J. Discrete Math. Sci. Cryptogr., vol. 29, no. 1, pp. 199–214 (2026).
[13] A. O. Mulani and P. B. Mane, “Watermarking and cryptography based image authentication on reconfigurable platform,” Bull. Elect. Eng. Informatics, vol. 6, no. 2, pp. 181–187 (2017).
[14] H. S. Deshpande, K. J. Karande, and A. O. Mulani, “Efficient implementation of AES algorithm on FPGA,” in Proc. 2014 Int. Conf. Commun. Signal Process. (ICCSP), Melmaruvathur, India, pp. 1895–1899 (2014), doi: 10.1109/ICCSP.2014.6950174.
[15] D. P. Mane and A. O. Mulani, “High throughput and area efficient FPGA implementation of AES algorithm,” Int. J. Eng. Adv. Technol., vol. 8, no. 4, pp. 519–523 (2019).
[16] H. S. Deshpande, K. J. Karande, and A. O. Mulani, “Area optimized implementation of AES algorithm on FPGA,” in Proc. 2015 Int. Conf. Commun. Signal Process. (ICCSP), Melmaruvathur, India, pp. 10–14 (2015), doi: 10.1109/ICCSP.2015.7322746.
