Privacy Preserving Inference Over Encrypted Data



Privacy preserving, homomorphic encryption, secured learning, federated learning


Machine learning and deep learning techniques provide solution to various medical applications relevant to disease detection. Many a time’s these learning algorithms and their inferences are generated in untrusted environments like cloud. Medical practitioners would like to protect their data in such cases in untrusted environments but would like to generate an inference on their data. Our work provides a solution to generate privacy preserving inference over encrypted data in such untrusted environment like public cloud. HELib based fully homomorphic encryption approach is used to provide security to the trained model and the data of the owner. Our results shows the effectiveness of using the technique to generate inference on encrypted data without comprising the accuracy of the system. Our work demonstrates on benchmark datasets like MNIST for prototyping and heart disease detection that are used by many machine learning applications for benchmarking.


Download data is not yet available.


N. Schlitter, A Protocol for Privacy Preserving Neural Network Learning on Horizontal Partitioned Data, Proc. Privacy Statistics in Databases (PSD 08), Sept. 2008

Nouby M. Ghazaly, A. H. H. . (2022). A Review of Using Natural Gas in Internal Combustion Engines. International Journal on Recent Technologies in Mechanical and Electrical Engineering, 9(2), 07–12.

T. Chen and S. Zhong,Privacy-Preserving Backpropagation Neural Network Learning, IEEE Trans. Neural Network, vol. 20, no. 10, pp. 1554-1564, Oct. 2009.

Sudhakar, C. V., & Reddy, G. U. . (2022). Land use Land cover change Assessment at Cement Industrial area using Landsat data-hybrid classification in part of YSR Kadapa District, Andhra Pradesh, India. International Journal of Intelligent Systems and Applications in Engineering, 10(1), 75–86.

Avhankar, M. S. ., D. J. A. . Pawar, S. . Majalekar, and S. . Kedari. “Mobile Ad Hoc Network Routing Protocols – Using OPNET Simulator”. International Journal on Recent and Innovation Trends in Computing and Communication, vol. 10, no. 1, Jan. 2022, pp. 01-07, doi:10.17762/ijritcc.v10i1.5513.

Ghazaly, N. M. . (2022). Data Catalogue Approaches, Implementation and Adoption: A Study of Purpose of Data Catalogue. International Journal on Future Revolution in Computer Science &Amp; Communication Engineering, 8(1), 01–04.

Nathan Dowlin, Ran Gilad-Bachrach, Kim Laine, Kristin Lauter, Michael Naehrig and John Wernsing, CryptoNets: Applying Neural Networks to Encrypted Data with High Throughput and Accuracy 29 December 2015

A generic framework for privacy preserving deep learning, Theo Ryffel, Andrew Trask, Morten Dahl, Bobby Wagner, Jason Mancuso, Daniel Rueckert, Jonathan Passerat-Palmbach, 13 Nov 2018.

Privacy Preserving Back-Propagation Neural Network Learning Made Practical with Cloud Computing. IEEE Transactions on Parallel and Distributed Systems, Vol. 25, No. 1, January 2014.

PySyft. [Online]. Available:

Sharma, V. . (2022). Unique Functors of Everywhere Connected Homomorphisms and the Countability of Groups. International Journal on Recent Trends in Life Science and Mathematics, 9(2), 01–09.

Knott, Brian and Venkataraman, Shobha and Hannun, Awni and Sengupta, Shubho and Ibrahim, Mark and van der Maaten, Laurens, CrypTen: Secure Multi-Party Computation Meets Machine Learning,, 2021

UCI Machine Learning Heart Disease Dataset:

HElib [Online]. Available:

N. A. Libre. (2021). A Discussion Platform for Enhancing Students Interaction in the Online Education. Journal of Online Engineering Education, 12(2), 07–12. Retrieved from

Li Li, Yuxi Fan, Mike Tse, Kuo-Yi Lin, A review of applications in federated learning, Computers & Industrial Engineering, Volume 149, 2020

Conceptual Idea of Privacy Preserving Inference




How to Cite

S. . Sayyad and D. . Kulkarni, “Privacy Preserving Inference Over Encrypted Data”, Int J Intell Syst Appl Eng, vol. 10, no. 3, pp. 129–134, Oct. 2022.



Research Article