Secure Aggregation with Top-K Sparsification in Decentralized Federated Learning

• URL: http://arxiv.org/abs/2606.10780v1
• Date: Tue, 09 Jun 2026 12:33:53 GMT
• Title: Secure Aggregation with Top-K Sparsification in Decentralized Federated Learning
• Abstract summary: Top-K gradient sparsification is an effective approach to reduce communication by transmitting only a few entries of the full gradient.<n>This paper studies information-theoretic secure aggregation with top-K sparsification in decentralized federated learning under user dropouts and user collusion.<n>We propose a communication-efficient sparse secure aggregation scheme that offloads dimension-dependent overhead to an offline phase.
• Score: 30.552991787966988
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Secure aggregation is a vital component for mitigating gradient leakage in federated learning, but its communication cost conventionally scales with the gradient dimension. This becomes prohibitive for large models and even more pronounced in decentralized federated learning with limited bandwidth and unreliable nodes. Top-K gradient sparsification is an effective approach to reduce communication by transmitting only a few entries of the full gradient, while maintaining competitive model accuracy. Nevertheless, the top-K entries selected by each user are unpredictable and vary across users, which poses a challenge for efficient sparse secure aggregation. This paper studies information-theoretic secure aggregation with top-K sparsification in decentralized federated learning under user dropouts and user collusion. We propose a communication-efficient sparse secure aggregation scheme that offloads dimension-dependent overhead to an offline phase and protects private gradients using random masks and permutations. Experimental results demonstrate that our scheme preserves accuracy comparable to full-gradient aggregation even with only 1% gradient sparsification, while substantially reducing the communication cost.

Related papers

• Information-Theoretically Secure Aggregation for Lightweight Federated Learning: Resilient to Dropouts and Adversaries [13.867315751451494]
  We propose a lightweight and information-theoretically secure aggregation framework tailored for sign-based FL.<n>The framework securely computes the majority vote (MV) through single-round secure multiplication.<n>These techniques reduce online communication by up to 99.5% and latency by up to 85.7% compared to conventional approaches.
  arXiv  Detail & Related papers  (2026-07-23T03:26:41Z)
• Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization [56.95448807869383]
  Federated Learning (FL) has emerged as a compelling paradigm for privacy-preserving distributed machine learning.<n>Recent studies find that the gradients exchanged in the FL system are also vulnerable to privacy leakage.<n>We propose textbfGradient textbfInversion over textbfFeature textbfDomains (GIFD)
  arXiv  Detail & Related papers  (2026-04-01T14:32:15Z)
• LSHFed: Robust and Communication-Efficient Federated Learning with Locally-Sensitive Hashing Gradient Mapping [27.641729042448194]
  Federated learning (FL) enables collaborative model training across distributed nodes without exposing raw data.<n>Inference attacks may recover sensitive information from gradient updates, while poisoning attacks can degrade model performance or induce malicious behaviors.<n>We propose LSHFed, a robust and communication-efficient FL framework that simultaneously enhances aggregation and privacy preservation.
  arXiv  Detail & Related papers  (2025-11-03T07:28:14Z)
• Secure Aggregation Meets Sparsification in Decentralized Learning [1.7010199949406575]
  This paper introduces CESAR, a novel secure aggregation protocol for Decentralized Learning (DL) CESAR provably defends against honest-but-curious adversaries and can be formally adapted to counteract collusion between them.
  arXiv  Detail & Related papers  (2024-05-13T12:52:58Z)
• Efficient and Secure Federated Learning for Financial Applications [15.04345368582332]
  This article proposes two sparsification methods to reduce communication cost in federated learning. One is a time-varying hierarchical sparsification method for model parameter update, which solves the problem of maintaining model accuracy after high ratio sparsity. The other is to apply the sparsification method to the secure aggregation framework.
  arXiv  Detail & Related papers  (2023-03-15T04:15:51Z)
• Magnitude Matters: Fixing SIGNSGD Through Magnitude-Aware Sparsification in the Presence of Data Heterogeneity [60.791736094073]
  Communication overhead has become one of the major bottlenecks in the distributed training of deep neural networks. We propose a magnitude-driven sparsification scheme, which addresses the non-convergence issue of SIGNSGD. The proposed scheme is validated through experiments on Fashion-MNIST, CIFAR-10, and CIFAR-100 datasets.
  arXiv  Detail & Related papers  (2023-02-19T17:42:35Z)
• Over-the-Air Federated Learning with Privacy Protection via Correlated Additive Perturbations [57.20885629270732]
  We consider privacy aspects of wireless federated learning with Over-the-Air (OtA) transmission of gradient updates from multiple users/agents to an edge server. Traditional perturbation-based methods provide privacy protection while sacrificing the training accuracy. In this work, we aim at minimizing privacy leakage to the adversary and the degradation of model accuracy at the edge server.
  arXiv  Detail & Related papers  (2022-10-05T13:13:35Z)
• Sparsified Secure Aggregation for Privacy-Preserving Federated Learning [1.2891210250935146]
  We propose a lightweight gradient sparsification framework for secure aggregation. Our theoretical analysis demonstrates that the proposed framework can significantly reduce the communication overhead of secure aggregation. Our experiments demonstrate that our framework reduces the communication overhead by up to 7.8x, while also speeding up the wall clock training time by 1.13x, when compared to conventional secure aggregation benchmarks.
  arXiv  Detail & Related papers  (2021-12-23T22:44:21Z)
• Sparse Communication for Training Deep Networks [56.441077560085475]
  Synchronous gradient descent (SGD) is the most common method used for distributed training of deep learning models. In this algorithm, each worker shares its local gradients with others and updates the parameters using the average gradients of all workers. We study several compression schemes and identify how three key parameters affect the performance.
  arXiv  Detail & Related papers  (2020-09-19T17:28:11Z)
• Differentially Private Federated Learning with Laplacian Smoothing [72.85272874099644]
  Federated learning aims to protect data privacy by collaboratively learning a model without sharing private data among users. An adversary may still be able to infer the private training data by attacking the released model. Differential privacy provides a statistical protection against such attacks at the price of significantly degrading the accuracy or utility of the trained models.
  arXiv  Detail & Related papers  (2020-05-01T04:28:38Z)
• Detached Error Feedback for Distributed SGD with Random Sparsification [98.98236187442258]
  Communication bottleneck has been a critical problem in large-scale deep learning. We propose a new distributed error feedback (DEF) algorithm, which shows better convergence than error feedback for non-efficient distributed problems. We also propose DEFA to accelerate the generalization of DEF, which shows better bounds than DEF.
  arXiv  Detail & Related papers  (2020-04-11T03:50:59Z)

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.