Gabriel Henrique Nunes

Gabriel Henrique Nunes
Federal University of Minas Gerais | UFMG · Departamento de Ciência da Computação

MSc
PhD Candidate

About

5
Publications
35
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2
Citations
Introduction
Doctoral candidate in Computer Science at the Federal University of Minas Gerais (UFMG), Brazil. Master in Computer Science and Bachelor in Physics from UFMG. Interested in Formal Methods, Quantitative Information Flow, Responsible Computing, Artificial Intelligence, and Neuroscience.
Education
July 2021 - June 2025
Federal University of Minas Gerais
Field of study
  • Computer Science
March 2019 - April 2021
Federal University of Minas Gerais
Field of study
  • Computer Science
March 2014 - August 2018

Publications

Publications (5)
Conference Paper
In this paper we study the relationship between privacy and accuracy in the context of correlated datasets. We use a model of quantitative information flow to describe the the trade-off between privacy of individuals' data and and the utility of queries to that data by modelling the effectiveness of adversaries attempting to make inferences after a...
Thesis
Privacy preservation in the release of statistical data has been a concern of the scientific community for decades. This preoccupation has been gradually expanding to outside of academia, and has been reflected in the widespread enactment and reinforcement of privacy-protection legislation around the world. In Brazil, the new privacy law enacted in...
Conference Paper
We present a summary of the work done in the dissertation "A formal quantitative study of privacy in the publication of official educational censuses in Brazil", including its contributions and impacts so far. The dissertation presents a systematic refactoring of the conventional treatment of privacy analyses, based on mathematical concepts from th...
Conference Paper
We present a systematic refactoring of the conventional treatment of privacy analyses, basing it on mathematical concepts from the framework of Quantitative Information Flow (QIF ). The approach we suggest brings three principal advantages: it is flexible, allowing for precise quantification and comparison of privacy risks for attacks both known an...
Preprint
Full-text available
We present a systematic refactoring of the conventional treatment of privacy analyses, basing it on mathematical concepts from the framework of Quantitative Information Flow (QIF). The approach we suggest brings three principal advantages: it is flexible, allowing for precise quantification and comparison of privacy risks for attacks both known and...