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

arXiv: https://arxiv.org/abs/2305.04288 · HTML: https://mlsanity.com/paper/2305.04288/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 42 references that are in the map.
- First posted on arXiv 7 May 2023.

## Builds on (most cited first, 19 of 19)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Inverting Gradients -- How easy is it to break privacy in federated learning?](https://mlsanity.com/paper/2003.14053/) (2020)
- [Federated Optimization: Distributed Machine Learning for On-Device Intelligence](https://mlsanity.com/paper/1610.02527/) (2016)
- [Differentially Private Federated Learning: A Client Level Perspective](https://mlsanity.com/paper/1712.07557/) (2017)
- [iDLG: Improved Deep Leakage from Gradients](https://mlsanity.com/paper/2001.02610/) (2020)
- [See through Gradients: Image Batch Recovery via GradInversion](https://mlsanity.com/paper/2104.07586/) (2021)
- [Distributed learning of deep neural network over multiple agents](https://mlsanity.com/paper/1810.06060/) (2018)
- [LDP-Fed: Federated Learning with Local Differential Privacy](https://mlsanity.com/paper/2006.03637/) (2020)
- [Locally Private Graph Neural Networks](https://mlsanity.com/paper/2006.05535/) (2020)
- [No Free Lunch Theorem for Security and Utility in Federated Learning](https://mlsanity.com/paper/2203.05816/) (2022)
- [Trading Off Privacy, Utility and Efficiency in Federated Learning](https://mlsanity.com/paper/2209.00230/) (2022)
- [Privacy-preserving Federated Adversarial Domain Adaption over Feature Groups for Interpretability](https://mlsanity.com/paper/2111.10934/) (2021)
- [Mitigating Data Heterogeneity in Federated Learning with Data Augmentation](https://mlsanity.com/paper/2206.09979/) (2022)
- [Fast Federated Learning by Balancing Communication Trade-Offs](https://mlsanity.com/paper/2105.11028/) (2021)
- [Federated Deep Learning with Bayesian Privacy](https://mlsanity.com/paper/2109.13012/) (2021)
- [Enhanced Security and Privacy via Fragmented Federated Learning](https://mlsanity.com/paper/2207.05978/) (2022)

## Built on by (most cited first, 6 of 6)

- [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)
- [Theoretical Analysis of Privacy Leakage in Trustworthy Federated Learning: A Perspective from Linear Algebra and Optimization Theory](https://mlsanity.com/paper/2407.16735/) (2024)
- [Bridging Privacy and Robustness for Trustworthy Machine Learning](https://mlsanity.com/paper/2403.16591/) (2024)
- [A Unified Learn-to-Distort-Data Framework for Privacy-Utility Trade-off in Trustworthy Federated Learning](https://mlsanity.com/paper/2407.04751/) (2024)
- [Deciphering the Interplay between Attack and Protection Complexity in Privacy-Preserving Federated Learning](https://mlsanity.com/paper/2508.11907/) (2025)

## 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.