Evaluation of Concrete ML for Secure Viral Strain Classification with Homomorphic Encryption

DOI

10.2991/978-94-6463-684-0_12How to use a DOI?

Keywords

fully homomorphic encryption; viral strain classification; logistic regression; Concrete ML

Abstract

Machine learning (ML) techniques are increasingly being used in viral strain classification. Along with this increase use, it becomes more practical to outsource these machine learning computations to the cloud. However, there are privacy issues that surround the outsourcing of viral genomic data. Hence, we can use homomorphic encryption to address these privacy issues. In our work, we used Concrete ML to perform viral strain classification with machine learning using homomorphic encryption. We evaluated the performance of the models developed with Concrete ML and shown that its performance in classification is comparable to those of normal ML libraries. However, its performance in terms of computational time is slower than normal ML libraries.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Johann Benjamin Vivas
AU  - Richard Bryann Chua
PY  - 2025
DA  - 2025/04/30
TI  - Evaluation of Concrete ML for Secure Viral Strain Classification with Homomorphic Encryption
BT  - Proceedings of the  Workshop on Computation: Theory and Practice (WCTP 2024)
PB  - Atlantis Press
SP  - 179
EP  - 191
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-684-0_12
DO  - 10.2991/978-94-6463-684-0_12
ID  - Vivas2025
ER  -