# CorBin-FL: A Differentially Private Federated Learning Mechanism using Common Randomness

arXiv: https://arxiv.org/abs/2409.13133 · HTML: https://mlsanity.com/paper/2409.13133/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 20 Sep 2024.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [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)
- [Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data](https://mlsanity.com/paper/1610.05755/) (2016)
- [Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising](https://mlsanity.com/paper/1805.06530/) (2018)
- [cpSGD: Communication-efficient and differentially-private distributed SGD](https://mlsanity.com/paper/1805.10559/) (2018)
- [Distributed Mean Estimation with Limited Communication](https://mlsanity.com/paper/1611.00429/) (2016)
- [The Discrete Gaussian for Differential Privacy](https://mlsanity.com/paper/2004.00010/) (2020)
- [LDP-Fed: Federated Learning with Local Differential Privacy](https://mlsanity.com/paper/2006.03637/) (2020)
- [Protection Against Reconstruction and Its Applications in Private Federated Learning](https://mlsanity.com/paper/1812.00984/) (2018)
- [BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learning](https://mlsanity.com/paper/1905.06731/) (2019)
- [LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacy](https://mlsanity.com/paper/2007.15789/) (2020)
- [Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimation](https://mlsanity.com/paper/2304.01541/) (2023)
- [The Privacy Power of Correlated Noise in Decentralized Learning](https://mlsanity.com/paper/2405.01031/) (2024)
- [Correlated quantization for distributed mean estimation and optimization](https://mlsanity.com/paper/2203.04925/) (2022)
- [User-Level Differential Privacy With Few Examples Per User](https://mlsanity.com/paper/2309.12500/) (2023)
- [Correlated Privacy Mechanisms for Differentially Private Distributed Mean Estimation](https://mlsanity.com/paper/2407.03289/) (2024)
- [Learning with User-Level Local Differential Privacy](https://mlsanity.com/paper/2405.17079/) (2024)

## Built on by (most cited first, 1 of 1)

- [QuanCrypt-FL: Quantized Homomorphic Encryption with Pruning for Secure Federated Learning](https://mlsanity.com/paper/2411.05260/) (2024)

## Abstract (arXiv)

Federated learning (FL) has emerged as a promising framework for distributed machine learning. It enables collaborative learning among multiple clients, utilizing distributed data and computing resources. However, FL faces challenges in balancing privacy guarantees, communication efficiency, and overall model accuracy. In this work, we introduce CorBin-FL, a privacy mechanism that uses correlated binary stochastic quantization to achieve differential privacy while maintaining overall model accuracy. The approach uses secure multi-party computation techniques to enable clients to perform correlated quantization of their local model updates without compromising individual privacy. We provide theoretical analysis showing that CorBin-FL achieves parameter-level local differential privacy (PLDP), and that it asymptotically optimizes the privacy-utility trade-off between the mean square error utility measure and the PLDP privacy measure. We further propose AugCorBin-FL, an extension that, in addition to PLDP, achieves user-level and sample-level central differential privacy guarantees. For both mechanisms, we derive bounds on privacy parameters and mean squared error performance measures. Extensive experiments on MNIST and CIFAR10 datasets demonstrate that our mechanisms outperform existing differentially private FL mechanisms, including Gaussian and Laplacian mechanisms, in terms of model accuracy under equal PLDP privacy budgets.