Corpus ID: 231582963

On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times

  title={On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times},
  author={Yao Fu and Y. Zhou and Di Wu and Shui Yu and Yonggang Wen and Chao Li},
  • Yao Fu, Y. Zhou, +3 authors Chao Li
  • Published 2021
  • Computer Science
  • ArXiv
  • In spite that Federated Learning (FL) is well known for its privacy protection when training machine learning models among distributed clients collaboratively, recent studies have pointed out that the naive FL is susceptible to gradient leakage attacks. In the meanwhile, Differential Privacy (DP) emerges as a promising countermeasure to defend against gradient leakage attacks. However, the adoption of DP by clients in FL may significantly jeopardize the model accuracy. It is still an open… CONTINUE READING

    Figures and Tables from this paper


    Federated Learning With Differential Privacy: Algorithms and Performance Analysis
    • Kang Wei, Jun Li, +6 authors H. Poor
    • Computer Science, Mathematics
    • IEEE Transactions on Information Forensics and Security
    • 2020
    • 54
    • Highly Influential
    • PDF
    A Framework for Evaluating Gradient Leakage Attacks in Federated Learning
    • 14
    • PDF
    FedSel: Federated SGD under Local Differential Privacy with Top-k Dimension Selection
    • 6
    • PDF
    Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning
    • 119
    • PDF
    Differentially Private Federated Learning: A Client Level Perspective
    • 308
    • Highly Influential
    • PDF
    LDP-Fed: federated learning with local differential privacy
    • 13
    • PDF
    Wireless Federated Learning with Local Differential Privacy
    • 21
    • PDF
    The Value of Collaboration in Convex Machine Learning with Differential Privacy
    • 15
    • Highly Influential
    • PDF
    Differentially Private Meta-Learning
    • 20
    • PDF
    Protection Against Reconstruction and Its Applications in Private Federated Learning
    • 89
    • Highly Influential
    • PDF