mlsanityData to 14 Oct 2026

A Meta-learning Framework for Tuning Parameters of Protection Mechanisms in Trustworthy Federated Learning

arXiv 2305.18400 ↗First posted 28 May 2023cs.LG cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Trustworthy Federated Learning (TFL) typically leverages protection mechanisms to guarantee privacy. However, protection mechanisms inevitably introduce utility loss or efficiency reduction while protecting data privacy. Therefore, protection mechanisms and their parameters should be carefully chosen to strike an optimal tradeoff between textitprivacy leakage, textitutility loss, and textitefficiency reduction. To this end, federated learning practitioners need tools to measure the three factors and optimize the tradeoff between them to choose the protection mechanism that is most appropriate to the application at hand. Motivated by this requirement, we propose a framework that (1) formulates TFL as a problem of finding a protection mechanism to optimize the tradeoff between privacy leakage, utility loss, and efficiency reduction and (2) formally defines bounded measurements of the three factors. We then propose a meta-learning algorithm to approximate this optimization problem and find optimal protection parameters for representative protection mechanisms, including Randomization, Homomorphic Encryption, Secret Sharing, and Compression. We further design estimation algorithms to quantify these found optimal protection parameters in a practical horizontal federated learning setting and provide a theoretical analysis of the estimation error.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 25 of its 52 references that are in the map. First posted on arXiv 28 May 2023.

Builds on

25 of 52 references.

References · 25

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2016Deep Learning with Differential Privacycited by 2,728
  3. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  4. 2019Deep Leakage from Gradientscited by 1,021
  5. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  6. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 564
  7. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  8. 2020iDLG: Improved Deep Leakage from Gradientscited by 382
  9. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 326
  10. 2018Distributed learning of deep neural network over multiple agentscited by 279
  11. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 210
  12. 2019SecureBoost: A Lossless Federated Learning Frameworkcited by 176
13 more
  1. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 132
  2. 2019On a generalization of the Jensen-Shannon divergence and the JS-symmetrization of distances relying on abstract meanscited by 61
  3. 2022No Free Lunch Theorem for Security and Utility in Federated Learningcited by 39
  4. 2016On the Theory and Practice of Privacy-Preserving Bayesian Data Analysiscited by 35
  5. 2022Trading Off Privacy, Utility and Efficiency in Federated Learningcited by 33
  6. 2021Privacy-preserving Federated Adversarial Domain Adaption over Feature Groups for Interpretabilitycited by 28
  7. 2023From Robustness to Privacy and Backcited by 27
  8. 2013Local Privacy and Minimax Bounds: Sharp Rates for Probability Estimationcited by 19
  9. 2021Fast Federated Learning by Balancing Communication Trade-Offscited by 18
  10. 2021Federated Deep Learning with Bayesian Privacycited by 13
  11. 2023Optimizing Privacy, Utility and Efficiency in Constrained Multi-Objective Federated Learningcited by 12
  12. 2023Towards Achieving Near-optimal Utility for Privacy-Preserving Federated Learning via Data Generation and Parameter Distortioncited by 6
  13. 2023Theoretically Principled Federated Learning for Balancing Privacy and Utilitycited by 6

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3; 2025: 2.

6 papers.

  1. 2024Theoretical Analysis of Privacy Leakage in Trustworthy Federated Learning: A Perspective from Linear Algebra and Optimization Theorycited by 2
  2. 2023Personalized Federated Learning via Amortized Bayesian Meta-Learningcited by 1
  3. 2024Bridging Privacy and Robustness for Trustworthy Machine Learningcited by 1
  4. 2024A Unified Learn-to-Distort-Data Framework for Privacy-Utility Trade-off in Trustworthy Federated Learningcited by 0
  5. 2025FedEM: A Privacy-Preserving Framework for Concurrent Utility Preservation in Federated Learningcited by 0
  6. 2025Deciphering the Interplay between Attack and Protection Complexity in Privacy-Preserving Federated Learningcited by 0