Study on learning models and encrypted data wins award from SBMAC

The paper was written in a context in which the amount of data generated by people and companies is growing exponentially, leveraging the use of machine learning methods.
Mathematics
08 August 2023
Study on learning models and encrypted data wins award from SBMAC

A study called “A survey on fully homomorphic encryption with statistical applications” received one of this year’s Beatriz Neves Introductory Scientific Research Awards from the Brazilian Society of Applied and Computational Mathematics (SBMAC). The paper was written by Rener de Souza Oliveira, a student at Fundação Getulio Vargas’ School of Applied Mathematics (FGV EMAp), as his end-of-course paper. Developed under the guidance of Professor Rodrigo Targino, the study discusses fully homomorphic encryption, which is a special type of encryption method that allows some learning models to run on encrypted data while maintaining strong mathematical guarantees of privacy protection.

The paper was written in a context in which the amount of data generated by people and companies is growing exponentially, leveraging the use of machine learning methods. Oliveira’s work considers the statistical principle that the more data a model has access to, the more accurate it will be in predicting or representing reality.

According to the author, a problem arises when a model needs to deal with sensitive data, such as medical, financial or genomic records. In these cases, additional care must be taken to ensure the privacy of data owners, whether individuals or companies.

The Beatriz Neves Awards were created by SBMAC to encourage undergraduate students to participate in introductory scientific research activities in the field of applied and computational mathematics. The name of the awards pays tribute to Professor Beatriz Neves (1935-1986), who worked at Rio de Janeiro Federal University’s Institute of Mathematics.

“A survey on fully homomorphic encryption with statistical applications” is available in FGV’s Digital Library.

Esse site usa cookies

Nosso website coleta informações do seu dispositivo e da sua navegação e utiliza tecnologias como cookies para armazená-las e permitir funcionalidades como: melhorar o funcionamento técnico das páginas, mensurar a audiência do website e oferecer produtos e serviços relevantes por meio de anúncios personalizados. Para mais informações, acesse o nosso Aviso de Cookies e o nosso Aviso de Privacidade.