mlsanityData to 7 Oct 2026

A Unified Learn-to-Distort-Data Framework for Privacy-Utility Trade-off in Trustworthy Federated Learning

arXiv 2407.04751 ↗First posted 5 Jul 2024cs.LG cs.AI cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we first give an introduction to the theoretical basis of the privacy-utility equilibrium in federated learning based on Bayesian privacy definitions and total variation distance privacy definitions. We then present the textitLearn-to-Distort-Data framework, which provides a principled approach to navigate the privacy-utility equilibrium by explicitly modeling the distortion introduced by the privacy-preserving mechanism as a learnable variable and optimizing it jointly with the model parameters. We demonstrate the applicability of our framework to a variety of privacy-preserving mechanisms on the basis of data distortion and highlight its connections to related areas such as adversarial training, input robustness, and unlearnable examples. These connections enable leveraging techniques from these areas to design effective algorithms for privacy-utility equilibrium in federated learning under the textitLearn-to-Distort-Data framework.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 35 references that are in the map. First posted on arXiv 5 Jul 2024.

Builds on

22 of 35 references.

References · 22

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2019Advances and Open Problems in Federated Learningcited by 3,021
  5. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  6. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 349
  7. 2018Adversarial Logit Pairingcited by 224
  8. 2021Unlearnable Examples: Making Personal Data Unexploitablecited by 188
  9. 2017Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryptioncited by 174
  10. 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
  11. 2020UVeQFed: Universal Vector Quantization for Federated Learningcited by 103
  12. 2020Adaptive Gradient Sparsification for Efficient Federated Learning: An Online Learning Approachcited by 80
10 more
  1. 2021Improved OOD Generalization via Adversarial Training and Pre-trainingcited by 66
  2. 2021SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsificationcited by 46
  3. 2022No Free Lunch Theorem for Security and Utility in Federated Learningcited by 39
  4. 2023Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attackscited by 28
  5. 2013Local Privacy and Minimax Bounds: Sharp Rates for Probability Estimationcited by 19
  6. 2020Constraining Variational Inference with Geometric Jensen-Shannon Divergencecited by 17
  7. 2023Towards Achieving Near-optimal Utility for Privacy-Preserving Federated Learning via Data Generation and Parameter Distortioncited by 6
  8. 2023Theoretically Principled Federated Learning for Balancing Privacy and Utilitycited by 6
  9. 2023A Meta-learning Framework for Tuning Parameters of Protection Mechanisms in Trustworthy Federated Learningcited by 6
  10. 2023Probably Approximately Correct Federated Learningcited by 4

Built on by

Not cited yet.