CoVnita, an end-to-end privacy-preserving framework for SARS-CoV-2 classification

CoVnita, an end-to-end privacy-preserving framework for SARS-CoV-2 classification

Scientific Reports

10.1038/s41598-023-34535-8

http://dx.doi.org/10.1038/s41598-023-34535-8

Jun Jie Sim, Weizhuang Zhou, Fook Mun Chan, Meenatchi Sundaram Muthu Selva Annamalai, Xiaoxia Deng, Benjamin Hong Meng Tan, Khin Mi Mi Aung

Multidisciplinary

08 May 2023

Sim, J. J., Zhou, W., Chan, F. M., Annamalai, M. S. M. S., Deng, X., Tan, B. H. M., & Aung, K. M. M. (2023). CoVnita, an end-to-end privacy-preserving framework for SARS-CoV-2 classification. Scientific Reports, 13(1). https://doi.org/10.1038/s41598-023-34535-8

AbstractClassification of viral strains is essential in monitoring and managing the COVID-19 pandemic, but patient privacy and data security concerns often limit the extent of the open sharing of full viral genome sequencing data. We propose a framework called CoVnita, that supports private training of a classification model and secure inference with the same model. Using genomic sequences from eight common SARS-CoV-2 strains, we simulated scenarios where the data was distributed across multiple data providers. Our framework produces a private federated model, over 8 parties, with a classification AUROC of 0.99, given a privacy budget of $$\varepsilon =1$$ ε = 1 . The roundtrip time, from encryption to decryption, took a total of 0.298 s, with an amortized time of 74.5 ms per sample.

Attribution 4.0 International (CC BY 4.0)

This research / project is supported by the Agency for Science, Technology And Research (A*STAR), Singapore - IE2020 Advanced Manufacturing and Engineering (AME) Programmatic Program
Grant Reference no. : A19E3b0099

https://oar.a-star.edu.sg/communities-collections/articles/19093

2045-2322

Institute for Infocomm Research