# Communication-Computation Efficient Secure Aggregation for Federated Learning

arXiv: https://arxiv.org/abs/2012.05433 · HTML: https://mlsanity.com/paper/2012.05433/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Dec 2020.

## Built on by (most cited first, 18 of 18)

- [Eluding Secure Aggregation in Federated Learning via Model Inconsistency](https://mlsanity.com/paper/2111.07380/) (2021)
- [Securing Secure Aggregation: Mitigating Multi-Round Privacy Leakage in Federated Learning](https://mlsanity.com/paper/2106.03328/) (2021)
- [Topology-aware Federated Learning in Edge Computing: A Comprehensive Survey](https://mlsanity.com/paper/2302.02573/) (2023)
- [Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstruction](https://mlsanity.com/paper/2311.05808/) (2023)
- [Information Theoretic Secure Aggregation with User Dropouts](https://mlsanity.com/paper/2101.07750/) (2021)
- [Aggregation Service for Federated Learning: An Efficient, Secure, and More Resilient Realization](https://mlsanity.com/paper/2202.01971/) (2022)
- [SwiftAgg+: Achieving Asymptotically Optimal Communication Loads in Secure Aggregation for Federated Learning](https://mlsanity.com/paper/2203.13060/) (2022)
- [FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models](https://mlsanity.com/paper/2304.13407/) (2023)
- [Secure Aggregation for Federated Learning in Flower](https://mlsanity.com/paper/2205.06117/) (2022)
- [SwiftAgg: Communication-Efficient and Dropout-Resistant Secure Aggregation for Federated Learning with Worst-Case Security Guarantees](https://mlsanity.com/paper/2202.04169/) (2022)
- [ByzSecAgg: A Byzantine-Resistant Secure Aggregation Scheme for Federated Learning Based on Coded Computing and Vector Commitment](https://mlsanity.com/paper/2302.09913/) (2023)
- [FedREP: A Byzantine-Robust, Communication-Efficient and Privacy-Preserving Framework for Federated Learning](https://mlsanity.com/paper/2303.05206/) (2023)
- [DecentNeRFs: Decentralized Neural Radiance Fields from Crowdsourced Images](https://mlsanity.com/paper/2403.13199/) (2024)
- [MedLeak: Multimodal Medical Data Leakage in Secure Federated Learning with Crafted Models](https://mlsanity.com/paper/2407.09972/) (2024)
- [SPRITE: A Scalable Privacy-Preserving and Verifiable Collaborative Learning for Industrial IoT](https://mlsanity.com/paper/2203.11914/) (2022)
- [Federated Learning in Healthcare: Model Misconducts, Security, Challenges, Applications, and Future Research Directions -- A Systematic Review](https://mlsanity.com/paper/2405.13832/) (2024)
- [EBS-CFL: Efficient and Byzantine-robust Secure Clustered Federated Learning](https://mlsanity.com/paper/2506.13612/) (2025)
- [The Capacity of Information-Theoretic Secure Aggregation in Federated Learning](https://mlsanity.com/paper/2606.07277/) (2026)

## Abstract (arXiv)

Federated learning has been spotlighted as a way to train neural networks using distributed data with no need for individual nodes to share data. Unfortunately, it has also been shown that adversaries may be able to extract local data contents off model parameters transmitted during federated learning. A recent solution based on the secure aggregation primitive enabled privacy-preserving federated learning, but at the expense of significant extra communication/computational resources. In this paper, we propose a low-complexity scheme that provides data privacy using substantially reduced communication/computational resources relative to the existing secure solution. The key idea behind the suggested scheme is to design the topology of secret-sharing nodes as a sparse random graph instead of the complete graph corresponding to the existing solution. We first obtain the necessary and sufficient condition on the graph to guarantee both reliability and privacy. We then suggest using the ErdHos-R'enyi graph in particular and provide theoretical guarantees on the reliability/privacy of the proposed scheme. Through extensive real-world experiments, we demonstrate that our scheme, using only 20 ~ 30% of the resources required in the conventional scheme, maintains virtually the same levels of reliability and data privacy in practical federated learning systems.