skip to main content
Idioma:
Primo Advanced Search
Primo Advanced Search Query Term
Primo Advanced Search Query Term
Primo Advanced Search Query Term
Primo Advanced Search prefilters
Busca Simples

Privacy preservation in federated learning: An insightful survey from the GDPR perspective

Truong, Nguyen ; Sun, Kai ; Wang, Siyao ; Guitton, Florian ; Guo, YiKe

Computers & security, 2021-11, Vol.110, p.102402, Article 102402 [Periódico revisado por pares]

Amsterdam: Elsevier Ltd

Texto completo disponível

Citações Citado por
  • Título:
    Privacy preservation in federated learning: An insightful survey from the GDPR perspective
  • Autor: Truong, Nguyen ; Sun, Kai ; Wang, Siyao ; Guitton, Florian ; Guo, YiKe
  • Assuntos: Computer privacy ; Data integrity ; Data protection regulation ; Federated learning ; GDPR ; General Data Protection Regulation ; Machine learning ; Parameter sensitivity ; Personal data ; Privacy ; Privacy preservation
  • É parte de: Computers & security, 2021-11, Vol.110, p.102402, Article 102402
  • Descrição: •Provide a novel systematic analysis on privacy preservation in Federated Learning (FL) taking into account the system architecture, threat models, different types of attack as well as the existing solutions in a centralised FL framework.•Conduct a comprehensive survey on privacy-preservation study in centralised FL framework following the structure from the systematic analysis.•Provide insightful examination on pros and cons of the existing privacy-preserving techniques as well as prospective solution approaches in order for a FL-based service to comply with the EU/UK General Data Protection Regulation (GDPR). [Display omitted] In recent years, along with the blooming of Machine Learning (ML)-based applications and services, ensuring data privacy and security have become a critical obligation. ML-based service providers not only confront with difficulties in collecting and managing data across heterogeneous sources but also challenges of complying with rigorous data protection regulations such as EU/UK General Data Protection Regulation (GDPR). Furthermore, conventional centralised ML approaches have always come with long-standing privacy risks to personal data leakage, misuse, and abuse. Federated learning (FL) has emerged as a prospective solution that facilitates distributed collaborative learning without disclosing original training data. Unfortunately, retaining data and computation on-device as in FL are not sufficient for privacy-guarantee because model parameters exchanged among participants conceal sensitive information that can be exploited in privacy attacks. Consequently, FL-based systems are not naturally compliant with the GDPR. This article is dedicated to surveying of state-of-the-art privacy-preservation techniques in FL in relations with GDPR requirements. Furthermore, insights into the existing challenges are examined along with the prospective approaches following the GDPR regulatory guidelines that FL-based systems shall implement to fully comply with the GDPR.
  • Editor: Amsterdam: Elsevier Ltd
  • Idioma: Inglês
Voltar para lista de resultados
Ir para página anteriorAnterior Resultado  6 AvançarIr para próxima página

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.