Training Machine Learning Models on Encrypted Data: A Privacy-Preserving Framework using Homomorphic Encryption

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Marques, Alexandre, Sá, Beatriz, Botelho, Rui, Pinto, Pedro
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917436604809216
author Marques, Alexandre
Sá, Beatriz
Botelho, Rui
Pinto, Pedro
author_facet Marques, Alexandre
Sá, Beatriz
Botelho, Rui
Pinto, Pedro
contents The use of Machine Learning (ML) for data-driven decision-making often relies on access to sensitive datasets, which introduces privacy challenges. Traditional encryption methods protect data at rest or in transit but fail to secure it during processing, exposing it to unauthorized access. Homomorphic encryption emerges as a transformative solution, enabling computations on encrypted data without decryption, thus preserving confidentiality throughout the ML pipeline. This paper addresses the challenge of training ML models on encrypted data while maintaining accuracy and efficiency by proposing a proof-of-concept for a privacy-preserving framework that leverages Cheon-Kim-Kim-Song (CKKS) for approximate real-number arithmetic. Also, it demonstrates the feasibility of training K-Nearest Neighbors (KNN) and linear regression models on encrypted data, and evaluates encrypted inference for a basic Multilayer Perceptron (MLP) architecture. Experimental results show that models trained under Homomorphic encryption achieve performance metrics comparable to plaintext-trained models, validating the approach. However, challenges such as computational overhead, noise management, and limited support for non-polynomial operations persist. This work lays the groundwork for broader adoption of privacy-preserving ML in real-world applications, balancing security with computational feasibility.
format Preprint
id arxiv_https___arxiv_org_abs_2604_23245
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Training Machine Learning Models on Encrypted Data: A Privacy-Preserving Framework using Homomorphic Encryption
Marques, Alexandre
Sá, Beatriz
Botelho, Rui
Pinto, Pedro
Cryptography and Security
Artificial Intelligence
E.3
The use of Machine Learning (ML) for data-driven decision-making often relies on access to sensitive datasets, which introduces privacy challenges. Traditional encryption methods protect data at rest or in transit but fail to secure it during processing, exposing it to unauthorized access. Homomorphic encryption emerges as a transformative solution, enabling computations on encrypted data without decryption, thus preserving confidentiality throughout the ML pipeline. This paper addresses the challenge of training ML models on encrypted data while maintaining accuracy and efficiency by proposing a proof-of-concept for a privacy-preserving framework that leverages Cheon-Kim-Kim-Song (CKKS) for approximate real-number arithmetic. Also, it demonstrates the feasibility of training K-Nearest Neighbors (KNN) and linear regression models on encrypted data, and evaluates encrypted inference for a basic Multilayer Perceptron (MLP) architecture. Experimental results show that models trained under Homomorphic encryption achieve performance metrics comparable to plaintext-trained models, validating the approach. However, challenges such as computational overhead, noise management, and limited support for non-polynomial operations persist. This work lays the groundwork for broader adoption of privacy-preserving ML in real-world applications, balancing security with computational feasibility.
title Training Machine Learning Models on Encrypted Data: A Privacy-Preserving Framework using Homomorphic Encryption
topic Cryptography and Security
Artificial Intelligence
E.3
url https://arxiv.org/abs/2604.23245