# Randomized Quantization is All You Need for Differential Privacy in Federated Learning

arXiv: https://arxiv.org/abs/2306.11913 · HTML: https://mlsanity.com/paper/2306.11913/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 29 references that are in the map.
- First posted on arXiv 20 Jun 2023.

## Builds on (most cited first, 14 of 14)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [Differentially Private Federated Learning: A Client Level Perspective](https://mlsanity.com/paper/1712.07557/) (2017)
- [FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization](https://mlsanity.com/paper/1909.13014/) (2019)
- [RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response](https://mlsanity.com/paper/1407.6981/) (2014)
- [Federated Learning with Compression: Unified Analysis and Sharp Guarantees](https://mlsanity.com/paper/2007.01154/) (2020)
- [cpSGD: Communication-efficient and differentially-private distributed SGD](https://mlsanity.com/paper/1805.10559/) (2018)
- [QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding](https://mlsanity.com/paper/1610.02132/) (2016)
- [The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation](https://mlsanity.com/paper/2102.06387/) (2021)
- [Learning with User-Level Privacy](https://mlsanity.com/paper/2102.11845/) (2021)
- [The Skellam Mechanism for Differentially Private Federated Learning](https://mlsanity.com/paper/2110.04995/) (2021)
- [Privacy for Free: Communication-Efficient Learning with Differential Privacy Using Sketches](https://mlsanity.com/paper/1911.00972/) (2019)
- [Privacy-Aware Compression for Federated Data Analysis](https://mlsanity.com/paper/2203.08134/) (2022)

## Built on by (most cited first, 17 of 17)

- [Layered Randomized Quantization for Communication-Efficient and Privacy-Preserving Distributed Learning](https://mlsanity.com/paper/2312.07060/) (2023)
- [Secure Aggregation is Not Private Against Membership Inference Attacks](https://mlsanity.com/paper/2403.17775/) (2024)
- [On the Impact of Uncertainty and Calibration on Likelihood-Ratio Membership Inference Attacks](https://mlsanity.com/paper/2402.10686/) (2024)
- [Membership Inference Risks in Quantized Models: A Theoretical and Empirical Study](https://mlsanity.com/paper/2502.06567/) (2025)
- [FedECA: Federated External Control Arms for Causal Inference with Time-To-Event Data in Distributed Settings](https://mlsanity.com/paper/2311.16984/) (2023)
- [NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA](https://mlsanity.com/paper/2411.03730/) (2024)
- [Privacy-Aware Randomized Quantization via Linear Programming](https://mlsanity.com/paper/2406.02599/) (2024)
- [Towards Federated Learning with On-device Training and Communication in 8-bit Floating Point](https://mlsanity.com/paper/2407.02610/) (2024)
- [DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling](https://mlsanity.com/paper/2509.03472/) (2025)
- [Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy](https://mlsanity.com/paper/2604.23426/) (2026)
- [A Quantization-based Technique for Privacy Preserving Distributed Learning](https://mlsanity.com/paper/2406.19418/) (2024)
- [PBM-VFL: Vertical Federated Learning with Feature and Sample Privacy](https://mlsanity.com/paper/2501.13916/) (2025)
- [Privacy-Preserving Quantized Federated Learning with Diverse Precision](https://mlsanity.com/paper/2507.00920/) (2025)
- [Federated learning over physical channels: adaptive algorithms with near-optimal guarantees](https://mlsanity.com/paper/2509.02538/) (2025)
- [FedFusion: Federated Learning with Diversity- and Cluster-Aware Encoders for Robust Adaptation under Label Scarcity](https://mlsanity.com/paper/2509.19220/) (2025)
- [Communication-Efficient Federated AUC Maximization with Cyclic Client Participation](https://mlsanity.com/paper/2601.01649/) (2026)
- [SoK: Enhancing Cryptographic Collaborative Learning with Differential Privacy](https://mlsanity.com/paper/2601.09460/) (2026)

## Abstract (arXiv)

Federated learning (FL) is a common and practical framework for learning a machine model in a decentralized fashion. A primary motivation behind this decentralized approach is data privacy, ensuring that the learner never sees the data of each local source itself. Federated learning then comes with two majors challenges: one is handling potentially complex model updates between a server and a large number of data sources; the other is that de-centralization may, in fact, be insufficient for privacy, as the local updates themselves can reveal information about the sources' data. To address these issues, we consider an approach to federated learning that combines quantization and differential privacy. Absent privacy, Federated Learning often relies on quantization to reduce communication complexity. We build upon this approach and develop a new algorithm called the Randomized Quantization Mechanism (RQM), which obtains privacy through a two-levels of randomization. More precisely, we randomly sub-sample feasible quantization levels, then employ a randomized rounding procedure using these sub-sampled discrete levels. We are able to establish that our results preserve ``Renyi differential privacy'' (Renyi DP). We empirically study the performance of our algorithm and demonstrate that compared to previous work it yields improved privacy-accuracy trade-offs for DP federated learning. To the best of our knowledge, this is the first study that solely relies on randomized quantization without incorporating explicit discrete noise to achieve Renyi DP guarantees in Federated Learning systems.