Hi-SAFE: Hierarchical Secure Aggregation for Lightweight Federated Learning
Not on the map. Why?
Abstract (arXiv)
Federated learning (FL) faces challenges in ensuring both privacy and communication efficiency, particularly in resource-constrained environments such as Internet of Things (IoT) and edge networks. While sign-based methods, such as sign stochastic gradient descent with majority voting (SIGNSGD-MV), offer substantial bandwidth savings, they remain vulnerable to inference attacks due to exposure of gradient signs. Existing secure aggregation techniques are either incompatible with sign-based methods or incur prohibitive overhead. To address these limitations, we propose Hi-SAFE, a lightweight and cryptographically secure aggregation framework for sign-based FL. Our core contribution is the construction of efficient majority vote polynomials for SIGNSGD-MV, derived from Fermat's Little Theorem. This formulation represents the majority vote as a low-degree polynomial over a finite field, enabling secure evaluation that hides intermediate values and reveals only the final result. We further introduce a hierarchical subgrouping strategy that ensures constant multiplicative depth and bounded per-user complexity, independent of the number of users n.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 23 of its 49 references that are in the map. First posted on arXiv 24 Nov 2025.
Builds on
23 of 49 references.
References · 23
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
- 2019Advances and Open Problems in Federated Learningcited by 3,046
- 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
- 2019Deep Leakage from Gradientscited by 1,021
- 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
- 2018signSGD: Compressed Optimisation for Non-Convex Problemscited by 571
- 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 408
- 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 334
- 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 210
- 2020Privacy and Robustness in Federated Learning: Attacks and Defensescited by 166
- 2021LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learningcited by 64
11 more
- 2020Differentially Private Secure Multi-Party Computation for Federated Learning in Financial Applicationscited by 58
- 2021Privacy-preserving Federated Learning based on Multi-key Homomorphic Encryptioncited by 48
- 2020Stochastic-Sign SGD for Federated Learning with Theoretical Guaranteescited by 35
- 2022Federated Learning for Medical Applications: A Taxonomy, Current Trends, Challenges, and Future Research Directionscited by 35
- 2023A Survey on Vertical Federated Learning: From a Layered Perspectivecited by 30
- 2021Gradient Leakage Attack Resilient Deep Learningcited by 18
- 2021FLASHE: Additively Symmetric Homomorphic Encryption for Cross-Silo Federated Learningcited by 15
- 2022Tighter Regret Analysis and Optimization of Online Federated Learningcited by 14
- 2021DP-SIGNSGD: When Efficiency Meets Privacy and Robustnesscited by 11
- 2023Sparse-SignSGD with Majority Vote for Communication-Efficient Distributed Learningcited by 3
- 2023AHSecAgg and TSKG: Lightweight Secure Aggregation for Federated Learning Without Compromisecited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.