Tesis doctoralsDepartament d'Enginyeria Informàtica i Matemàtiques

Protecting Models and Data in Federated and Centralized Learning

  • Identification data

    Identifier:  TDX:4174
    Authors:  Jebreel, Najeeb Moharram Salim
    Abstract:
    Federated Learning (FL) is a technique that enables a global machine learning model to be learned from data that is distributed among participating peers, coordinated by a server. FL offers several benefits, including reduced computation costs, the ability to train more accurate models, and improved privacy. However, FL is vulnerable to various security and privacy attacks due to its distributed nature. To address this, this thesis proposes four defenses against poisoning and privacy attacks in the FL paradigm, including a method to neutralize Byzantine poisoning attacks, a technique to extract relevant gradients to counter label-flipping attacks, a method to mitigate targeted poisoning attacks, and fragmented federated learning to balance security, privacy, and accuracy. In addition, the thesis proposes two more defenses against backdoor and model stealing attacks that can be used in both federated and centralized learning. Experimental results demonstrate the effectiveness of these defenses in making machine learning more secure and private.
  • Others:

    Publisher: Universitat Rovira i Virgili
    Date: 2023-07-04, 2023-07-26T22:45:25Z, 2023-07-26T09:32:09Z
    Identifier: http://hdl.handle.net/10803/688858
    Departament/Institute: Departament d'Enginyeria Informàtica i Matemàtiques, Universitat Rovira i Virgili.
    Language: eng
    Author: Jebreel, Najeeb Moharram Salim
    Director: Sánchez Ruenes, David, Domingo Ferrer, Josep
    Source: TDX (Tesis Doctorals en Xarxa)
    Format: application/pdf, 268 p.
  • Keywords:

    Security attacks
    Privacy attacks
    Federated learning
    Ataques a la seguridad
    Ataques a la privacidad
    Aprendizaje federado
    Atacs a la seguretat
    Atacs a la privadesa
    Aprenentatge federat
    Ciències
  • Documents:

  • Cerca a google

    Search to google scholar