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

arXiv: https://arxiv.org/abs/2407.04751 · HTML: https://mlsanity.com/paper/2407.04751/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 5 Jul 2024.

## Builds on (most cited first, 22 of 22)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Exploiting Unintended Feature Leakage in Collaborative Learning](https://mlsanity.com/paper/1805.04049/) (2018)
- [FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization](https://mlsanity.com/paper/1909.13014/) (2019)
- [Adversarial Logit Pairing](https://mlsanity.com/paper/1803.06373/) (2018)
- [Unlearnable Examples: Making Personal Data Unexploitable](https://mlsanity.com/paper/2101.04898/) (2021)
- [Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption](https://mlsanity.com/paper/1711.10677/) (2017)
- [Improving the Robustness of Deep Neural Networks via Stability Training](https://mlsanity.com/paper/1604.04326/) (2016)
- [UVeQFed: Universal Vector Quantization for Federated Learning](https://mlsanity.com/paper/2006.03262/) (2020)
- [Adaptive Gradient Sparsification for Efficient Federated Learning: An Online Learning Approach](https://mlsanity.com/paper/2001.04756/) (2020)
- [Improved OOD Generalization via Adversarial Training and Pre-training](https://mlsanity.com/paper/2105.11144/) (2021)
- [SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification](https://mlsanity.com/paper/2112.06274/) (2021)
- [No Free Lunch Theorem for Security and Utility in Federated Learning](https://mlsanity.com/paper/2203.05816/) (2022)
- [Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attacks](https://mlsanity.com/paper/2303.15127/) (2023)
- [Local Privacy and Minimax Bounds: Sharp Rates for Probability Estimation](https://mlsanity.com/paper/1305.6000/) (2013)
- [Constraining Variational Inference with Geometric Jensen-Shannon Divergence](https://mlsanity.com/paper/2006.10599/) (2020)
- [Towards Achieving Near-optimal Utility for Privacy-Preserving Federated Learning via Data Generation and Parameter Distortion](https://mlsanity.com/paper/2305.04288/) (2023)
- [Theoretically Principled Federated Learning for Balancing Privacy and Utility](https://mlsanity.com/paper/2305.15148/) (2023)
- [A Meta-learning Framework for Tuning Parameters of Protection Mechanisms in Trustworthy Federated Learning](https://mlsanity.com/paper/2305.18400/) (2023)
- [Probably Approximately Correct Federated Learning](https://mlsanity.com/paper/2304.04641/) (2023)

## 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.