mlsanityData to 7 Oct 2026

Towards Achieving Near-optimal Utility for Privacy-Preserving Federated Learning via Data Generation and Parameter Distortion

arXiv 2305.04288 ↗First posted 7 May 2023cs.LG cs.AI cs.CRcited by 6

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) enables participating parties to collaboratively build a global model with boosted utility without disclosing private data information. Appropriate protection mechanisms have to be adopted to fulfill the requirements in preserving textitprivacy and maintaining high model textitutility. The nature of the widely-adopted protection mechanisms including textitRandomization Mechanism and textitCompression Mechanism is to protect privacy via distorting model parameter. We measure the utility via the gap between the original model parameter and the distorted model parameter. We want to identify under what general conditions privacy-preserving federated learning can achieve near-optimal utility via data generation and parameter distortion. To provide an avenue for achieving near-optimal utility, we present an upper bound for utility loss, which is measured using two main terms called variance-reduction and model parameter discrepancy separately. Our analysis inspires the design of appropriate protection parameters for the protection mechanisms to achieve near-optimal utility and meet the privacy requirements simultaneously. The main techniques for the protection mechanism include parameter distortion and data generation, which are generic and can be applied extensively. Furthermore, we provide an upper bound for the trade-off between privacy and utility, bluewhich together with the lower bound provided by no free lunch theorem in federated learning (citezhang2022no) form the conditions for achieving optimal trade-off.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 19 of its 42 references that are in the map. First posted on arXiv 7 May 2023.

Builds on

19 of 42 references.

References · 19

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2016Deep Learning with Differential Privacycited by 2,682
  3. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  4. 2019Deep Leakage from Gradientscited by 1,004
  5. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  6. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  7. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  8. 2020iDLG: Improved Deep Leakage from Gradientscited by 367
  9. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 320
  10. 2018Distributed learning of deep neural network over multiple agentscited by 277
  11. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 129
  12. 2020Locally Private Graph Neural Networkscited by 64
7 more
  1. 2022No Free Lunch Theorem for Security and Utility in Federated Learningcited by 39
  2. 2022Trading Off Privacy, Utility and Efficiency in Federated Learningcited by 33
  3. 2021Privacy-preserving Federated Adversarial Domain Adaption over Feature Groups for Interpretabilitycited by 28
  4. 2022Mitigating Data Heterogeneity in Federated Learning with Data Augmentationcited by 21
  5. 2021Fast Federated Learning by Balancing Communication Trade-Offscited by 18
  6. 2021Federated Deep Learning with Bayesian Privacycited by 13
  7. 2022Enhanced Security and Privacy via Fragmented Federated Learningcited by 3

Built on by

Cited by year

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

6 papers.

  1. 2023Theoretically Principled Federated Learning for Balancing Privacy and Utilitycited by 6
  2. 2023A Meta-learning Framework for Tuning Parameters of Protection Mechanisms in Trustworthy Federated Learningcited by 6
  3. 2024Theoretical Analysis of Privacy Leakage in Trustworthy Federated Learning: A Perspective from Linear Algebra and Optimization Theorycited by 2
  4. 2024Bridging Privacy and Robustness for Trustworthy Machine Learningcited by 1
  5. 2024A Unified Learn-to-Distort-Data Framework for Privacy-Utility Trade-off in Trustworthy Federated Learningcited by 0
  6. 2025Deciphering the Interplay between Attack and Protection Complexity in Privacy-Preserving Federated Learningcited by 0