Articles producció científica> Enginyeria Informàtica i Matemàtiques

A Critical Review on the Use (and Misuse) of Differential Privacy in Machine Learning

  • Datos identificativos

    Identificador: imarina:9289126
    Autores:
    Blanco-Justicia, AlbertoSanchez, DavidDomingo-Ferrer, JosepMuralidhar, Krishnamurty
    Resumen:
    We review the use of differential privacy (DP) for privacy protection in machine learning (ML). We show that, driven by the aim of preserving the accuracy of the learned models, DP-based ML implementations are so loose that they do not offer the ex ante privacy guarantees of DP. Instead, what they deliver is basically noise addition similar to the traditional (and often criticized) statistical disclosure control approach. Due to the lack of formal privacy guarantees, the actual level of privacy offered must be experimentally assessed ex post , which is done very seldom. In this respect, we present empirical results showing that standard anti-overfitting techniques in ML can achieve a better utility/privacy/efficiency tradeoff than DP.
  • Otros:

    Autor según el artículo: Blanco-Justicia, Alberto; Sanchez, David; Domingo-Ferrer, Josep; Muralidhar, Krishnamurty
    Departamento: Enginyeria Informàtica i Matemàtiques
    Autor/es de la URV: Blanco Justicia, Alberto / Domingo Ferrer, Josep / Sánchez Ruenes, David
    Palabras clave: Machine learning Federated learning Differential privacy Data utility machine learning federated learning data utility
    Resumen: We review the use of differential privacy (DP) for privacy protection in machine learning (ML). We show that, driven by the aim of preserving the accuracy of the learned models, DP-based ML implementations are so loose that they do not offer the ex ante privacy guarantees of DP. Instead, what they deliver is basically noise addition similar to the traditional (and often criticized) statistical disclosure control approach. Due to the lack of formal privacy guarantees, the actual level of privacy offered must be experimentally assessed ex post , which is done very seldom. In this respect, we present empirical results showing that standard anti-overfitting techniques in ML can achieve a better utility/privacy/efficiency tradeoff than DP.
    Áreas temáticas: Theoretical computer science Medicina ii Matemática / probabilidade e estatística Interdisciplinar General computer science Engenharias iv Computer science, theory & methods Computer science (miscellaneous) Computer science (all) Ciência da computação Astronomia / física
    Acceso a la licencia de uso: https://creativecommons.org/licenses/by/3.0/es/
    Direcció de correo del autor: alberto.blanco@urv.cat david.sanchez@urv.cat josep.domingo@urv.cat
    Identificador del autor: 0000-0002-1108-8082 0000-0001-7275-7887 0000-0001-7213-4962
    Fecha de alta del registro: 2024-10-12
    Versión del articulo depositado: info:eu-repo/semantics/acceptedVersion
    Enlace a la fuente original: https://dl.acm.org/doi/10.1145/3547139
    URL Documento de licencia: https://repositori.urv.cat/ca/proteccio-de-dades/
    Referencia al articulo segun fuente origial: Acm Computing Surveys. 55 (8): 1-16
    Referencia de l'ítem segons les normes APA: Blanco-Justicia, Alberto; Sanchez, David; Domingo-Ferrer, Josep; Muralidhar, Krishnamurty (2023). A Critical Review on the Use (and Misuse) of Differential Privacy in Machine Learning. Acm Computing Surveys, 55(8), 1-16. DOI: 10.1145/3547139
    DOI del artículo: 10.1145/3547139
    Entidad: Universitat Rovira i Virgili
    Año de publicación de la revista: 2023
    Tipo de publicación: Journal Publications
  • Palabras clave:

    Computer Science (Miscellaneous),Computer Science, Theory & Methods,Theoretical Computer Science
    Machine learning
    Federated learning
    Differential privacy
    Data utility
    machine learning
    federated learning
    data utility
    Theoretical computer science
    Medicina ii
    Matemática / probabilidade e estatística
    Interdisciplinar
    General computer science
    Engenharias iv
    Computer science, theory & methods
    Computer science (miscellaneous)
    Computer science (all)
    Ciência da computação
    Astronomia / física
  • Documentos:

  • Cerca a google

    Search to google scholar