# Federated Learning with Local Differential Privacy: Trade-offs between Privacy, Utility, and Communication

arXiv: https://arxiv.org/abs/2102.04737 · HTML: https://mlsanity.com/paper/2102.04737/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 9 Feb 2021.

## Builds on (most cited first, 12 of 12)

- [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 with Differential Privacy: Algorithms and Performance Analysis](https://mlsanity.com/paper/1911.00222/) (2019)
- [Differentially Private Federated Learning: A Client Level Perspective](https://mlsanity.com/paper/1712.07557/) (2017)
- [The Composition Theorem for Differential Privacy](https://mlsanity.com/paper/1311.0776/) (2013)
- [Collecting Telemetry Data Privately](https://mlsanity.com/paper/1712.01524/) (2017)
- [LDP-Fed: Federated Learning with Local Differential Privacy](https://mlsanity.com/paper/2006.03637/) (2020)
- [UVeQFed: Universal Vector Quantization for Federated Learning](https://mlsanity.com/paper/2006.03262/) (2020)
- [LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacy](https://mlsanity.com/paper/2007.15789/) (2020)
- [Wireless Federated Learning with Local Differential Privacy](https://mlsanity.com/paper/2002.05151/) (2020)
- [FedSel: Federated SGD under Local Differential Privacy with Top-k Dimension Selection](https://mlsanity.com/paper/2003.10637/) (2020)
- [A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via f-Divergences](https://mlsanity.com/paper/2001.05990/) (2020)

## Built on by (most cited first, 30 of 39)

- [No Free Lunch Theorem for Security and Utility in Federated Learning](https://mlsanity.com/paper/2203.05816/) (2022)
- [Joint Privacy Enhancement and Quantization in Federated Learning](https://mlsanity.com/paper/2208.10888/) (2022)
- [One Parameter Defense -- Defending against Data Inference Attacks via Differential Privacy](https://mlsanity.com/paper/2203.06580/) (2022)
- [A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiency](https://mlsanity.com/paper/2307.10655/) (2023)
- [Securing Distributed SGD against Gradient Leakage Threats](https://mlsanity.com/paper/2305.06473/) (2023)
- [FedLess: Secure and Scalable Federated Learning Using Serverless Computing](https://mlsanity.com/paper/2111.03396/) (2021)
- [The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscape](https://mlsanity.com/paper/2405.03636/) (2024)
- [Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-Ray Data](https://mlsanity.com/paper/2205.03168/) (2022)
- [Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off](https://mlsanity.com/paper/2402.07002/) (2024)
- [FLSys: Toward an Open Ecosystem for Federated Learning Mobile Apps](https://mlsanity.com/paper/2111.09445/) (2021)
- [Client-Level Differential Privacy via Adaptive Intermediary in Federated Medical Imaging](https://mlsanity.com/paper/2307.12542/) (2023)
- [Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss](https://mlsanity.com/paper/2402.05453/) (2024)
- [Federated Learning with Heterogeneous Differential Privacy](https://mlsanity.com/paper/2110.15252/) (2021)
- [Privacy Preservation in Artificial Intelligence and Extended Reality (AI-XR) Metaverses: A Survey](https://mlsanity.com/paper/2310.10665/) (2023)
- [FedLesScan: Mitigating Stragglers in Serverless Federated Learning](https://mlsanity.com/paper/2211.05739/) (2022)
- [Personalized DP-SGD using Sampling Mechanisms](https://mlsanity.com/paper/2305.15165/) (2023)
- [Age Aware Scheduling for Differentially-Private Federated Learning](https://mlsanity.com/paper/2405.05962/) (2024)
- [Communication-Efficient and Privacy-Adaptable Mechanism for Federated Learning](https://mlsanity.com/paper/2501.12046/) (2025)
- [The More, the Better? A Study on Collaborative Machine Learning for DGA Detection](https://mlsanity.com/paper/2109.11830/) (2021)
- [A New Dimensionality Reduction Method Based on Hensel's Compression for Privacy Protection in Federated Learning](https://mlsanity.com/paper/2205.02089/) (2022)
- [Matching Pursuit Based Scheduling for Over-the-Air Federated Learning](https://mlsanity.com/paper/2206.06679/) (2022)
- [Optimal Privacy Preserving for Federated Learning in Mobile Edge Computing](https://mlsanity.com/paper/2211.07166/) (2022)
- [Balancing Privacy and Performance for Private Federated Learning Algorithms](https://mlsanity.com/paper/2304.05127/) (2023)
- [Differentially Private Wireless Federated Learning Using Orthogonal Sequences](https://mlsanity.com/paper/2306.08280/) (2023)
- [Federated Learning with Reduced Information Leakage and Computation](https://mlsanity.com/paper/2310.06341/) (2023)
- [Exposing the Vulnerability of Decentralized Learning to Membership Inference Attacks Through the Lens of Graph Mixing](https://mlsanity.com/paper/2412.12837/) (2024)
- [PAUSE: Low-Latency and Privacy-Aware Active User Selection for Federated Learning](https://mlsanity.com/paper/2503.13173/) (2025)
- [Communication-Efficient and Privacy-Adaptable Mechanism -- a Federated Learning Scheme with Convergence Analysis](https://mlsanity.com/paper/2601.10701/) (2026)
- [Exploring the Benefits of Differentially Private Pre-training and Parameter-Efficient Fine-tuning for Table Transformers](https://mlsanity.com/paper/2309.06526/) (2023)
- [Data Quality in Edge Machine Learning: A State-of-the-Art Survey](https://mlsanity.com/paper/2406.02600/) (2024)

## Abstract (arXiv)

Federated learning (FL) allows to train a massive amount of data privately due to its decentralized structure. Stochastic gradient descent (SGD) is commonly used for FL due to its good empirical performance, but sensitive user information can still be inferred from weight updates shared during FL iterations. We consider Gaussian mechanisms to preserve local differential privacy (LDP) of user data in the FL model with SGD. The trade-offs between user privacy, global utility, and transmission rate are proved by defining appropriate metrics for FL with LDP. Compared to existing results, the query sensitivity used in LDP is defined as a variable and a tighter privacy accounting method is applied. The proposed utility bound allows heterogeneous parameters over all users. Our bounds characterize how much utility decreases and transmission rate increases if a stronger privacy regime is targeted. Furthermore, given a target privacy level, our results guarantee a significantly larger utility and a smaller transmission rate as compared to existing privacy accounting methods.