Enhancing Model Privacy in Federated Learning with Random Masking and Quantization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Zhibo, Zhu, Jianhao, Xu, Jingwen, Lv, Changze, Huang, Zisu, Wang, Xiaohua, Wu, Muling, Qian, Qi, Zheng, Xiaoqing, Huang, Xuanjing
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916920267112448
author Xu, Zhibo
Zhu, Jianhao
Xu, Jingwen
Lv, Changze
Huang, Zisu
Wang, Xiaohua
Wu, Muling
Qian, Qi
Zheng, Xiaoqing
Huang, Xuanjing
author_facet Xu, Zhibo
Zhu, Jianhao
Xu, Jingwen
Lv, Changze
Huang, Zisu
Wang, Xiaohua
Wu, Muling
Qian, Qi
Zheng, Xiaoqing
Huang, Xuanjing
contents The primary goal of traditional federated learning is to protect data privacy by enabling distributed edge devices to collaboratively train a shared global model while keeping raw data decentralized at local clients. The rise of large language models (LLMs) has introduced new challenges in distributed systems, as their substantial computational requirements and the need for specialized expertise raise critical concerns about protecting intellectual property (IP). This highlights the need for a federated learning approach that can safeguard both sensitive data and proprietary models. To tackle this challenge, we propose FedQSN, a federated learning approach that leverages random masking to obscure a subnetwork of model parameters and applies quantization to the remaining parameters. Consequently, the server transmits only a privacy-preserving proxy of the global model to clients during each communication round, thus enhancing the model's confidentiality. Experimental results across various models and tasks demonstrate that our approach not only maintains strong model performance in federated learning settings but also achieves enhanced protection of model parameters compared to baseline methods.
format Preprint
id arxiv_https___arxiv_org_abs_2508_18911
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Model Privacy in Federated Learning with Random Masking and Quantization
Xu, Zhibo
Zhu, Jianhao
Xu, Jingwen
Lv, Changze
Huang, Zisu
Wang, Xiaohua
Wu, Muling
Qian, Qi
Zheng, Xiaoqing
Huang, Xuanjing
Machine Learning
Artificial Intelligence
The primary goal of traditional federated learning is to protect data privacy by enabling distributed edge devices to collaboratively train a shared global model while keeping raw data decentralized at local clients. The rise of large language models (LLMs) has introduced new challenges in distributed systems, as their substantial computational requirements and the need for specialized expertise raise critical concerns about protecting intellectual property (IP). This highlights the need for a federated learning approach that can safeguard both sensitive data and proprietary models. To tackle this challenge, we propose FedQSN, a federated learning approach that leverages random masking to obscure a subnetwork of model parameters and applies quantization to the remaining parameters. Consequently, the server transmits only a privacy-preserving proxy of the global model to clients during each communication round, thus enhancing the model's confidentiality. Experimental results across various models and tasks demonstrate that our approach not only maintains strong model performance in federated learning settings but also achieves enhanced protection of model parameters compared to baseline methods.
title Enhancing Model Privacy in Federated Learning with Random Masking and Quantization
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2508.18911