On Using Secure Aggregation in Differentially Private Federated Learning with Multiple Local Steps

Mikko A. Heikkilä
7/27/2024
cs.LGcs.CR

No official code found. Best implementation: mixheikk/DPFL-with-SecAgg-paper (0 stars, CC-BY-SA-4.0, last commit 2025-04-24).

Abstract

Federated learning is a distributed learning setting where the main aim is to train machine learning models without having to share raw data but only what is required for learning. To guarantee training data privacy and high-utility models, differential privacy and secure aggregation techniques are often combined with federated learning. However, with fine-grained protection granularities, e.g., with the common sample-level protection, the currently existing techniques generally require the parties to communicate for each local optimization step, if they want to fully benefit from the secure aggregation in terms of the resulting formal privacy guarantees. In this paper, we show how a simple new analysis allows the parties to perform multiple local optimization steps while still benefiting from using secure aggregation. We show that our analysis enables higher utility models with guaranteed privacy protection under limited number of communication rounds.

View on arXivView PDF

Code Implementations(1)

mixheikk/DPFL-with-SecAgg-paperCommunity59%
CC-BY-SA-4.0

Code for the paper "On Using Secure Aggregation in Differentially Private Federated Learning with Multiple Local Steps"

00C++, ShellMar 14, 20251 years agoCC-BY-SA-4.0

Similar Papers

Efficiently Achieving Secure Model Training and Secure Aggregation to Ensure Bidirectional Privacy-Preservation in Federated Learning

90% match2024

Client-specific Property Inference against Secure Aggregation in Federated Learning

89% match2023

Using Decentralized Aggregation for Federated Learning with Differential Privacy

89% match2023

Enhancing Federated Learning with Adaptive Differential Privacy and Priority-Based Aggregation

89% match2024

Balancing Privacy and Performance for Private Federated Learning Algorithms

89% match2023

Perfectly-Private Analog Secure Aggregation in Federated Learning

89% match2025

Cite this paper

@article{heikkil2024using,
  title  = {On Using Secure Aggregation in Differentially Private Federated Learning with Multiple Local Steps},
  author = {Mikko A. Heikkilä},
  year   = {2024},
  eprint = {2407.19286},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2407.19286v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2407.19286.svg)](https://codeofpaper.com/paper/2407.19286)

Discussion