Hi-SAFE: Hierarchical Secure Aggregation for Lightweight Federated Learning

• URL: http://arxiv.org/abs/2511.18887v1
• Date: Mon, 24 Nov 2025 08:42:40 GMT
• Title: Hi-SAFE: Hierarchical Secure Aggregation for Lightweight Federated Learning
• Authors: Hyeong-Gun Joo, Songnam Hong, Seunghwan Lee, Dong-Joon Shin,
• Abstract summary: We propose Hi-SAFE, a cryptographically secure aggregation framework for sign-based Federated learning.<n>Our core contribution is the construction of efficient majority votes for SIGNSGDMV, derived from Fermat's Little Theorem.<n>We further introduce a hierarchical subgrouping strategy that ensures constant multiplicative depth and bounded complexity.
• Score: 16.477223151835982
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• Hierarchical Federated Learning with SignSGD: A Highly Communication-Efficient Approach [16.51305515824504]
  Hierarchical edge learning (HFL) has emerged as a key for large-scale wireless and Internet of Things systems.<n>One method such as sign-based gradient descent (SignSGD) offer an essential solution, but existing theory and algorithms do not naturally extend to hierarchical settings.<n>We introduce a scalable HFL algorithm, HierSignSGD, and provide the convergence analysis for SignSGD in a hierarchical setting.
  arXiv  Detail & Related papers  (2026-02-02T17:18:03Z)
• Subgraph Federated Learning via Spectral Methods [52.40322201034717]
  FedLap is a novel framework that captures inter-node dependencies while ensuring privacy and scalability.<n>We provide a formal analysis of the privacy of FedLap, demonstrating that it preserves privacy.
  arXiv  Detail & Related papers  (2025-10-29T16:22:32Z)
• Constrained Adversarial Perturbation [16.05659740749269]
  Universal Adversarial Perturbations (UAPs) have emerged as a powerful tool for both stress testing model robustness and scalable adversarial training.<n>We propose Constrained Adversarial Perturbation (CAP), an efficient algorithm that solves this problem using a gradient based alternating optimization strategy.
  arXiv  Detail & Related papers  (2025-10-17T14:44:20Z)
• MARS-Sep: Multimodal-Aligned Reinforced Sound Separation [72.85468563236005]
  MARS-Sep is a reinforcement learning framework for sound separation.<n>It learns a factorized Beta mask policy that is optimized by a clipped trust-region surrogate.<n>Experiments on multiple benchmarks demonstrate consistent gains in Text-, Audio-, and Image-Queried separation.
  arXiv  Detail & Related papers  (2025-10-12T09:05:28Z)
• Analytic Rényi Entropy Bounds for Device-Independent Cryptography [0.0]
  Device-independent (DI) cryptography represents the highest level of security.<n>We provide a simple method to obtain tighter finite-size security proofs for protocols based on the CHSH game.
  arXiv  Detail & Related papers  (2025-07-10T01:15:28Z)
• Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling [9.774529150331297]
  Stratify is a novel FL framework designed to systematically manage class and feature distributions throughout training.<n>Inspired by classical stratified sampling, our approach employs a Stratified Label Schedule (SLS) to ensure balanced exposure across labels.<n>To uphold privacy, we implement a secure client selection protocol leveraging homomorphic encryption.
  arXiv  Detail & Related papers  (2025-04-18T04:44:41Z)
• Perfect Gradient Inversion in Federated Learning: A New Paradigm from the Hidden Subset Sum Problem [21.546869377126125]
  Federated Learning (FL) has emerged as a popular paradigm for collaborative learning among multiple parties. We formulate the input reconstruction problem using the gradient information shared in FL as the Hidden Subset Sum Problem. Our analysis provides insights into why empirical input reconstruction attacks degrade with larger batch sizes.
  arXiv  Detail & Related papers  (2024-09-21T23:01:33Z)
• Exploiting Low-confidence Pseudo-labels for Source-free Object Detection [54.98300313452037]
  Source-free object detection (SFOD) aims to adapt a source-trained detector to an unlabeled target domain without access to the labeled source data. Current SFOD methods utilize a threshold-based pseudo-label approach in the adaptation phase. We propose a new approach to take full advantage of pseudo-labels by introducing high and low confidence thresholds.
  arXiv  Detail & Related papers  (2023-10-19T12:59:55Z)
• GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization [52.55628139825667]
  Federated Learning (FL) has emerged as a promising distributed machine learning framework to preserve clients' privacy. Recent studies find that an attacker can invert the shared gradients and recover sensitive data against an FL system by leveraging pre-trained generative adversarial networks (GAN) as prior knowledge. We propose textbfGradient textbfInversion over textbfFeature textbfDomains (GIFD), which disassembles the GAN model and searches the feature domains of the intermediate layers.
  arXiv  Detail & Related papers  (2023-08-09T04:34:21Z)
• Is Vertical Logistic Regression Privacy-Preserving? A Comprehensive Privacy Analysis and Beyond [57.10914865054868]
  We consider vertical logistic regression (VLR) trained with mini-batch descent gradient. We provide a comprehensive and rigorous privacy analysis of VLR in a class of open-source Federated Learning frameworks.
  arXiv  Detail & Related papers  (2022-07-19T05:47:30Z)
• Generalizable Representation Learning for Mixture Domain Face Anti-Spoofing [53.82826073959756]
  Face anti-spoofing approach based on domain generalization(DG) has drawn growing attention due to its robustness forunseen scenarios. We propose domain dy-namic adjustment meta-learning (D2AM) without using do-main labels. To overcome the limitation, we propose domain dy-namic adjustment meta-learning (D2AM) without using do-main labels.
  arXiv  Detail & Related papers  (2021-05-06T06:04:59Z)
• Sharing classical secrets with continuous-variable entanglement: Composable security and network coding advantage [0.913755431537592]
  We show that multi-partite entangled resources achieve a genuine advantage over point-to-point protocols for quantum communication. This is the first concrete compelling examples of multi-partite entangled resources achieving a genuine advantage over point-to-point protocols for quantum communication.
  arXiv  Detail & Related papers  (2021-04-21T17:37:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.