Articles producció científica> Enginyeria Informàtica i Matemàtiques

Achieving security and privacy in federated learning systems: Survey, research challenges and future directions

  • Identification data

    Identifier: imarina:9228601
    Authors:
    Blanco-Justicia, AlbertoDomingo-Ferrer, JosepMartinez, SergioSanchez, DavidFlanagan, AdrianTan, Kuan Eeik
    Abstract:
    Federated learning (FL) allows a server to learn a machine learning (ML) model across multiple decentralized clients that privately store their own training data. In contrast with centralized ML approaches, FL saves computation to the server and does not require the clients to outsource their private data to the server. However, FL is not free of issues. On the one hand, the model updates sent by the clients at each training epoch might leak information on the clients’ private data. On the other hand, the model learnt by the server may be subjected to attacks by malicious clients; these security attacks might poison the model or prevent it from converging. In this paper, we first examine security and privacy attacks to FL and critically survey solutions proposed in the literature to mitigate each attack. Afterwards, we discuss the difficulty of simultaneously achieving security and privacy protection. Finally, we sketch ways to tackle this open problem and attain both security and privacy.
  • Others:

    Author, as appears in the article.: Blanco-Justicia, Alberto; Domingo-Ferrer, Josep; Martinez, Sergio; Sanchez, David; Flanagan, Adrian; Tan, Kuan Eeik
    Department: Enginyeria Informàtica i Matemàtiques
    URV's Author/s: Blanco Justicia, Alberto / Domingo Ferrer, Josep / Martinez Lluis, Sergio / Sánchez Ruenes, David
    Keywords: Self-enforcing protocols Security Privacy Machine learning Federated learning security privacy machine learning
    Abstract: Federated learning (FL) allows a server to learn a machine learning (ML) model across multiple decentralized clients that privately store their own training data. In contrast with centralized ML approaches, FL saves computation to the server and does not require the clients to outsource their private data to the server. However, FL is not free of issues. On the one hand, the model updates sent by the clients at each training epoch might leak information on the clients’ private data. On the other hand, the model learnt by the server may be subjected to attacks by malicious clients; these security attacks might poison the model or prevent it from converging. In this paper, we first examine security and privacy attacks to FL and critically survey solutions proposed in the literature to mitigate each attack. Afterwards, we discuss the difficulty of simultaneously achieving security and privacy protection. Finally, we sketch ways to tackle this open problem and attain both security and privacy.
    Thematic Areas: Robotics & automatic control Medicina i Materiais Matemática / probabilidade e estatística Linguística e literatura Interdisciplinar Engineering, multidisciplinary Engineering, electrical & electronic Engineering Engenharias iv Engenharias iii Engenharias ii Engenharias i Electrical and electronic engineering Control and systems engineering Computer science, artificial intelligence Ciências agrárias i Ciência de alimentos Ciência da computação Biotecnología Automation & control systems Artificial intelligence Administração pública e de empresas, ciências contábeis e turismo
    licence for use: https://creativecommons.org/licenses/by/3.0/es/
    Author's mail: alberto.blanco@urv.cat david.sanchez@urv.cat sergio.martinezl@urv.cat josep.domingo@urv.cat
    Author identifier: 0000-0002-1108-8082 0000-0001-7275-7887 0000-0002-3941-5348 0000-0001-7213-4962
    Record's date: 2024-10-12
    Papper version: info:eu-repo/semantics/publishedVersion
    Link to the original source: https://www.sciencedirect.com/science/article/pii/S095219762100316X?via%3Dihub
    Licence document URL: https://repositori.urv.cat/ca/proteccio-de-dades/
    Papper original source: Engineering Applications Of Artificial Intelligence. 106 (2021): 104468-
    APA: Blanco-Justicia, Alberto; Domingo-Ferrer, Josep; Martinez, Sergio; Sanchez, David; Flanagan, Adrian; Tan, Kuan Eeik (2021). Achieving security and privacy in federated learning systems: Survey, research challenges and future directions. Engineering Applications Of Artificial Intelligence, 106(2021), 104468-. DOI: 10.1016/j.engappai.2021.104468
    Article's DOI: 10.1016/j.engappai.2021.104468
    Entity: Universitat Rovira i Virgili
    Journal publication year: 2021
    Publication Type: Journal Publications
  • Keywords:

    Artificial Intelligence,Automation & Control Systems,Computer Science, Artificial Intelligence,Control and Systems Engineering,Electrical and Electronic Engineering,Engineering,Engineering, Electrical & Electronic,Engineering, Multidisciplinary,Robotics & Automatic Control
    Self-enforcing protocols
    Security
    Privacy
    Machine learning
    Federated learning
    security
    privacy
    machine learning
    Robotics & automatic control
    Medicina i
    Materiais
    Matemática / probabilidade e estatística
    Linguística e literatura
    Interdisciplinar
    Engineering, multidisciplinary
    Engineering, electrical & electronic
    Engineering
    Engenharias iv
    Engenharias iii
    Engenharias ii
    Engenharias i
    Electrical and electronic engineering
    Control and systems engineering
    Computer science, artificial intelligence
    Ciências agrárias i
    Ciência de alimentos
    Ciência da computação
    Biotecnología
    Automation & control systems
    Artificial intelligence
    Administração pública e de empresas, ciências contábeis e turismo
  • Documents:

  • Cerca a google

    Search to google scholar