Setup Once, Secure Always: A Single-Setup Secure Federated Learning Aggregation Protocol with Forward and Backward Secrecy for Dynamic Users

Federated Learning (FL) enables multiple users to collaboratively train a machine learning model without sharing raw data, making it suitable for privacy-sensitive applications. However, local model or weight updates can still leak sensitive information. Secure aggregation protocols mitigate this risk by ensuring that only the aggregated updates are revealed. Among these, single-setup protocols, where key generation and exchange occur only once, are the most efficient due to reduced communication and computation overhead. However, existing single-setup protocols often lack support for dynamic user participation and do not provide strong privacy guarantees such as forward and backward secrecy. \par In this paper, we present a novel secure aggregation protocol that requires only a single setup for the entire FL training. Our protocol supports dynamic user participation, tolerates dropouts, and achieves both forward and backward secrecy. It leverages lightweight symmetric homomorphic encryption with a key negation technique to mask updates efficiently, eliminating the need for user-to-user communication. To defend against model inconsistency attacks, we introduce a low-overhead verification mechanism using message authentication codes (MACs). We provide formal security proofs under both semi-honest and malicious adversarial models and implement a full prototype. Experimental results show that our protocol reduces user-side computation by up to $99\%$ compared to state-of-the-art protocols like e-SeaFL (ACSAC'24), while maintaining competitive model accuracy. These features make our protocol highly practical for real-world FL deployments, especially on resource-constrained devices.

• Publication year

  2025

• Venue

  Unknown venue

• Publication date

  2025-02-13

• Fields of study

  Computer Science

• Identifiers
  arXiv 2502.08989
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Privacy-preserving federated learning with intermediate-level model sharing

  2025cited by this paper
• RaSA: Robust and Adaptive Secure Aggregation for Edge-Assisted Hierarchical Federated Learning

  2025cited by this paper
• MicroSecAgg: Streamlined Single-Server Secure Aggregation

  2024cited by this paper
• Uncovering Attacks and Defenses in Secure Aggregation for Federated Deep Learning

  2024cited by this paper
• When Federated Learning Meets Privacy-Preserving Computation

  2024cited by this paper
• Efficient Verifiable Protocol for Privacy-Preserving Aggregation in Federated Learning

  2023cited by this paper
• Flamingo: Multi-Round Single-Server Secure Aggregation with Applications to Private Federated Learning

  2023cited by this paper
• FedShare: Secure Aggregation based on Additive Secret Sharing in Federated Learning

  2023cited by this paper
• Fast Secure Aggregation With High Dropout Resilience for Federated Learning

  2023cited by this paper
• Efficient Secure Aggregation for Privacy-Preserving Federated Machine Learning

  2023cited by this paper
• PPA: Preference Profiling Attack Against Federated Learning

  2022cited by this paper
• PFLF: Privacy-Preserving Federated Learning Framework for Edge Computing

  2022cited by this paper
• Privacy-Preserving Aggregation in Federated Learning: A Survey

  2022cited by this paper
• Fixing Issues and Achieving Maliciously Secure Verifiable Aggregation in "VeriFL: Communication-Efficient and Fast Verifiable Aggregation for Federated Learning"

  2022cited by this paper
• The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation

  2021cited by this paper
• CrypTen: Secure Multi-Party Computation Meets Machine Learning

  2021cited by this paper
• SAFELearn: Secure Aggregation for private FEderated Learning

  2021cited by this paper
• A Comprehensive Survey of Privacy-preserving Federated Learning

  2021cited by this paper
• Gradient Inversion with Generative Image Prior

  2021cited by this paper
• Eluding Secure Aggregation in Federated Learning via Model Inconsistency

  2021cited by this paper
• LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learning

  2021cited by this paper
• Secure Single-Server Aggregation with (Poly)Logarithmic Overhead

  2020cited by this paper
• POSEIDON: Privacy-Preserving Federated Neural Network Learning

  2020cited by this paper
• Federated Latent Dirichlet Allocation: A Local Differential Privacy Based Framework

  2020cited by this paper
• Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning

  2020cited by this paper
• VerifyNet: Secure and Verifiable Federated Learning

  2020cited by this paper
• BatchCrypt: Efficient Homomorphic Encryption for Cross-Silo Federated Learning

  2020cited by this paper
• Inverting Gradients - How easy is it to break privacy in federated learning?

  2020cited by this paper
• Deep Leakage from Gradients

  2019cited by this paper
• Federated Learning With Differential Privacy: Algorithms and Performance Analysis

  2019cited by this paper
• When Edge Meets Learning: Adaptive Control for Resource-Constrained Distributed Machine Learning

  2018cited by this paper
• Privacy-Preserving Deep Learning via Additively Homomorphic Encryption

  2018cited by this paper
• SecureML: A System for Scalable Privacy-Preserving Machine Learning

  2017cited by this paper
• Practical Secure Aggregation for Privacy-Preserving Machine Learning

  2017cited by this paper
• Communication-Efficient Learning of Deep Networks from Decentralized Data

  2016cited by this paper
• Privacy-Preserving Stream Aggregation with Fault Tolerance

  2012cited by this paper
• Learning Multiple Layers of Features from Tiny Images

  2009cited by this paper
• Gradient-based learning applied to document recognition

  1998cited by this paper

• Per-element Secure Aggregation against Data Reconstruction Attacks in Federated Learning

  2025cites this paper