# Efficient Secure Aggregation for Privacy-Preserving Federated Machine Learning

arXiv: https://arxiv.org/abs/2304.03841 · HTML: https://mlsanity.com/paper/2304.03841/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2023.

## Built on by (most cited first, 7 of 7)

- [Communication-Efficient and Tensorized Federated Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2410.13097/) (2024)
- [FheFL: Fully Homomorphic Encryption Friendly Privacy-Preserving Federated Learning with Byzantine Users](https://mlsanity.com/paper/2306.05112/) (2023)
- [Uncovering Attacks and Defenses in Secure Aggregation for Federated Deep Learning](https://mlsanity.com/paper/2410.09676/) (2024)
- [Secure Aggregation for Privacy-Preserving Federated Learning on Clinical EEG Data](https://mlsanity.com/paper/2607.28191/) (2026)
- [Setup Once, Secure Always: A Single-Setup Secure Federated Learning Aggregation Protocol with Forward and Backward Secrecy for Dynamic Users](https://mlsanity.com/paper/2502.08989/) (2025)
- [Beyond Weights and Gradients: A Taxonomy of Federated Learning Messages](https://mlsanity.com/paper/2606.16891/) (2026)
- [End-to-End Verifiable and Robust Federated Learning](https://mlsanity.com/paper/2609.15521/) (2026)

## Abstract (arXiv)

Secure aggregation protocols ensure the privacy of users' data in federated learning by preventing the disclosure of local gradients. Many existing protocols impose significant communication and computational burdens on participants and may not efficiently handle the large update vectors typical of machine learning models. Correspondingly, we present e-SeaFL, an efficient verifiable secure aggregation protocol taking only one communication round during the aggregation phase. e-SeaFL allows the aggregation server to generate proof of honest aggregation to participants via authenticated homomorphic vector commitments. Our core idea is the use of assisting nodes to help the aggregation server, under similar trust assumptions existing works place upon the participating users. Our experiments show that the user enjoys an order of magnitude efficiency improvement over the state-of-the-art (IEEE S&P 2023) for large gradient vectors with thousands of parameters. Our open-source implementation is available at https://github.com/vt-asaplab/e-SeaFL.