# Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation

arXiv: https://arxiv.org/abs/2509.25906 · HTML: https://mlsanity.com/paper/2509.25906/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 61 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 30 of 34)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [On the Convergence of FedAvg on Non-IID Data](https://mlsanity.com/paper/1907.02189/) (2019)
- [Exploiting Shared Representations for Personalized Federated Learning](https://mlsanity.com/paper/2102.07078/) (2021)
- [Federated Learning with Differential Privacy: Algorithms and Performance Analysis](https://mlsanity.com/paper/1911.00222/) (2019)
- [Split learning for health: Distributed deep learning without sharing raw patient data](https://mlsanity.com/paper/1812.00564/) (2018)
- [SplitFed: When Federated Learning Meets Split Learning](https://mlsanity.com/paper/2004.12088/) (2020)
- [Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergences](https://mlsanity.com/paper/1807.01647/) (2018)
- [Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity](https://mlsanity.com/paper/1811.12469/) (2018)
- [FedPD: A Federated Learning Framework with Optimal Rates and Adaptivity to Non-IID Data](https://mlsanity.com/paper/2005.11418/) (2020)
- [LDP-Fed: Federated Learning with Local Differential Privacy](https://mlsanity.com/paper/2006.03637/) (2020)
- [Privacy Amplification by Iteration](https://mlsanity.com/paper/1808.06651/) (2018)
- [Federated Learning with Bayesian Differential Privacy](https://mlsanity.com/paper/1911.10071/) (2019)
- [On Safeguarding Privacy and Security in the Framework of Federated Learning](https://mlsanity.com/paper/1909.06512/) (2019)
- [Composition of Differential Privacy & Privacy Amplification by Subsampling](https://mlsanity.com/paper/2210.00597/) (2022)
- [Privacy Amplification via Random Check-Ins](https://mlsanity.com/paper/2007.06605/) (2020)
- [Stronger Privacy Amplification by Shuffling for R'enyi and Approximate Differential Privacy](https://mlsanity.com/paper/2208.04591/) (2022)
- [FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning](https://mlsanity.com/paper/2404.02478/) (2024)
- [Privacy Amplification for Federated Learning via User Sampling and Wireless Aggregation](https://mlsanity.com/paper/2103.01953/) (2021)
- [Privacy and Efficiency of Communications in Federated Split Learning](https://mlsanity.com/paper/2301.01824/) (2023)
- [PeFLL: Personalized Federated Learning by Learning to Learn](https://mlsanity.com/paper/2306.05515/) (2023)
- [Privacy Amplification for Matrix Mechanisms](https://mlsanity.com/paper/2310.15526/) (2023)
- [Privacy amplification by random allocation](https://mlsanity.com/paper/2502.08202/) (2025)
- [ULDP-FL: Federated Learning with Across Silo User-Level Differential Privacy](https://mlsanity.com/paper/2308.12210/) (2023)
- [Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learning](https://mlsanity.com/paper/2406.03519/) (2024)
- [Enhancing Accuracy-Privacy Trade-off in Differentially Private Split Learning](https://mlsanity.com/paper/2310.14434/) (2023)
- [Differentially Private Federated Clustering over Non-IID Data](https://mlsanity.com/paper/2301.00955/) (2023)
- [Distributed Learning over Networks with Graph-Attention-Based Personalization](https://mlsanity.com/paper/2305.13041/) (2023)
- [Differentially Private Federated Learning With Time-Adaptive Privacy Spending](https://mlsanity.com/paper/2502.18706/) (2025)

## Abstract (arXiv)

Federated Learning (FL) often adopts differential privacy (DP) to protect client data, but the added noise required for privacy guarantees can substantially degrade model accuracy. To resolve this challenge, we propose model-splitting privacy-amplified federated learning (MS-PAFL), a novel framework that combines structural model splitting with statistical privacy amplification. In this framework, each client's model is partitioned into a private submodel, retained locally, and a public submodel, shared for global aggregation. The calibrated Gaussian noise is injected only into the public submodel, thereby confining its adverse impact while preserving the utility of the local model. We further present a rigorous theoretical analysis that characterizes the joint privacy amplification achieved through random client participation and local data subsampling under this architecture. The analysis provides tight bounds on both single-round and total privacy loss, demonstrating that MS-PAFL significantly reduces the noise necessary to satisfy a target privacy protection level. Extensive experiments validate our theoretical findings, showing that MS-PAFL consistently attains a superior privacy-utility trade-off and enables the training of highly accurate models under strong privacy guarantees.