# Efficient Sparse Secure Aggregation for Federated Learning

arXiv: https://arxiv.org/abs/2007.14861 · HTML: https://mlsanity.com/paper/2007.14861/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2020.

## Built on by (most cited first, 6 of 6)

- [Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacy](https://mlsanity.com/paper/2202.07178/) (2022)
- [Machine Unlearning of Federated Clusters](https://mlsanity.com/paper/2210.16424/) (2022)
- [Information Theoretic Secure Aggregation with User Dropouts](https://mlsanity.com/paper/2101.07750/) (2021)
- [Just One Byte (per gradient): A Note on Low-Bandwidth Decentralized Language Model Finetuning Using Shared Randomness](https://mlsanity.com/paper/2306.10015/) (2023)
- [ScionFL: Efficient and Robust Secure Quantized Aggregation](https://mlsanity.com/paper/2210.07376/) (2022)
- [Secure Sparse Matrix Multiplications and their Applications to Privacy-Preserving Machine Learning](https://mlsanity.com/paper/2510.14894/) (2025)

## Abstract (arXiv)

Federated Learning enables one to jointly train a machine learning model across distributed clients holding sensitive datasets. In real-world settings, this approach is hindered by expensive communication and privacy concerns. Both of these challenges have already been addressed individually, resulting in competing optimisations. In this article, we tackle them simultaneously for one of the first times. More precisely, we adapt compression-based federated techniques to additive secret sharing, leading to an efficient secure aggregation protocol, with an adaptable security level. We prove its privacy against malicious adversaries and its correctness in the semi-honest setting. Experiments on deep convolutional networks demonstrate that our secure protocol achieves high accuracy with low communication costs. Compared to prior works on secure aggregation, our protocol has a lower communication and computation costs for a similar accuracy.