paper-with-me

홈 › Papers

FLUE: Federated Learning with Un-Encrypted model weights

2024-07-26 · Elie Atallah

Federated Learning enables diverse devices to collaboratively train a shared model while keeping training data locally stored, avoiding the need for centralized cloud storage. Despite existing privacy measures, concerns arise from potential reverse engineering of gradients, even with added noise, revealing private data. To address this, recent research emphasizes using encrypted model parameters during training. This paper introduces a novel federated learning algorithm, leveraging coded local gradients without encryption, exchanging coded proxies for model parameters, and injecting surplus noise for enhanced privacy. Two algorithm variants are presented, showcasing convergence and learning rates adaptable to coding schemes and raw data characteristics. Two encryption-free implementations with fixed and random coding matrices are provided, demonstrating promising simulation results from both federated optimization and machine learning perspectives.

📄 PDF Abstract BibTeX arXiv:2407.18750

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningFLUEmodel

Similar Papers 제목 키워드 기반

DictPFL: Efficient and Private Federated Learning on Encrypted Gradients

2025-10-24 · Jiaqi Xue, Mayank Kumar, Yuzhang Shang, Shangqian Gao 외 arxiv

Federated Learning (FL) enables collaborative model training across institutions without sharing raw data. However, gradient sharing still risks privacy leakage, such as gradient inversion attacks. Homomorphic Encryption…

Federated Learning

Efficient Federated Learning with Encrypted Data Sharing for Data-Heterogeneous Edge Devices

2025-06-25 · Hangyu Li, Hongyue Wu, Guodong Fan, Zhen Zhang 외

As privacy protection gains increasing importance, more models are being trained on edge devices and subsequently merged into the central server through Federated Learning (FL). However, current research overlooks the im…

Federated Learning

An End-to-End Encrypted Neural Network for Gradient Updates Transmission in Federated Learning

2019-08-22 · Hongyu Li, Tianqi Han

Federated learning is a distributed learning method to train a shared model by aggregating the locally-computed gradient updates. In federated learning, bandwidth and privacy are two main concerns of gradient updates tra…

Data CompressionFederated Learning

A Multiparty Homomorphic Encryption Approach to Confidential Federated Kaplan Meier Survival Analysis

2024-12-29 · Narasimha Raghavan Veeraragavan, Svetlana Boudko, Jan Franz Nygård

The proliferation of healthcare data has expanded opportunities for collaborative research, yet stringent privacy regulations hinder pooling sensitive patient records. We propose a \emph{multiparty homomorphic encryption…

Privacy PreservingReconstruction AttackSurvival Analysis

Robust Federated Learning via Byzantine Filtering over Encrypted Updates

2026-02-05 · Adda Akram Bendoukha, Aymen Boudguiga, Nesrine Kaaniche, Renaud Sirdey 외 arxiv

Federated Learning (FL) aims to train a collaborative model while preserving data privacy. However, the distributed nature of this approach still raises privacy and security issues, such as the exposure of sensitive data…

Federated Learning