# A Quantization-based Technique for Privacy Preserving Distributed Learning

arXiv: https://arxiv.org/abs/2406.19418 · HTML: https://mlsanity.com/paper/2406.19418/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 33 references that are in the map.
- First posted on arXiv 26 Jun 2024.

## Builds on (most cited first, 9 of 9)

- [cpSGD: Communication-efficient and differentially-private distributed SGD](https://mlsanity.com/paper/1805.10559/) (2018)
- [Hyperparameter Tuning with Renyi Differential Privacy](https://mlsanity.com/paper/2110.03620/) (2021)
- [Private Selection from Private Candidates](https://mlsanity.com/paper/1811.07971/) (2018)
- [Survey: Leakage and Privacy at Inference Time](https://mlsanity.com/paper/2107.01614/) (2021)
- [Randomized Quantization is All You Need for Differential Privacy in Federated Learning](https://mlsanity.com/paper/2306.11913/) (2023)
- [Composition Theorems for Interactive Differential Privacy](https://mlsanity.com/paper/2207.09397/) (2022)
- [Layered Randomized Quantization for Communication-Efficient and Privacy-Preserving Distributed Learning](https://mlsanity.com/paper/2312.07060/) (2023)
- [Killing Two Birds with One Stone: Quantization Achieves Privacy in Distributed Learning](https://mlsanity.com/paper/2304.13545/) (2023)
- [Unifying computational entropies via Kullback-Leibler divergence](https://mlsanity.com/paper/1902.11202/) (2019)

## Abstract (arXiv)

The massive deployment of Machine Learning (ML) models raises serious concerns about data protection. Privacy-enhancing technologies (PETs) offer a promising first step, but hard challenges persist in achieving confidentiality and differential privacy in distributed learning. In this paper, we describe a novel, regulation-compliant data protection technique for the distributed training of ML models, applicable throughout the ML life cycle regardless of the underlying ML architecture. Designed from the data owner's perspective, our method protects both training data and ML model parameters by employing a protocol based on a quantized multi-hash data representation Hash-Comb combined with randomization. The hyper-parameters of our scheme can be shared using standard Secure Multi-Party computation protocols. Our experimental results demonstrate the robustness and accuracy-preserving properties of our approach.