LF3PFL: A Practical Privacy-Preserving Federated Learning Algorithm Based on Local Federalization Scheme

Author:

Li Yong123ORCID,Xu Gaochao1,Meng Xutao2ORCID,Du Wei2ORCID,Ren Xianglin2

Affiliation:

1. School of Computer Science and Technology, Jilin University, Changchun 130012, China

2. School of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China

3. AI Research Institute, Changchun University of Technology, Changchun 130012, China

Abstract

In the realm of federated learning (FL), the exchange of model data may inadvertently expose sensitive information of participants, leading to significant privacy concerns. Existing FL privacy-preserving techniques, such as differential privacy (DP) and secure multi-party computing (SMC), though offering viable solutions, face practical challenges including reduced performance and complex implementations. To overcome these hurdles, we propose a novel and pragmatic approach to privacy preservation in FL by employing localized federated updates (LF3PFL) aimed at enhancing the protection of participant data. Furthermore, this research refines the approach by incorporating cross-entropy optimization, carefully fine-tuning measurement, and improving information loss during the model training phase to enhance both model efficacy and data confidentiality. Our approach is theoretically supported and empirically validated through extensive simulations on three public datasets: CIFAR-10, Shakespeare, and MNIST. We evaluate its effectiveness by comparing training accuracy and privacy protection against state-of-the-art techniques. Our experiments, which involve five distinct local models (Simple-CNN, ModerateCNN, Lenet, VGG9, and Resnet18), provide a comprehensive assessment across a variety of scenarios. The results clearly demonstrate that LF3PFL not only maintains competitive training accuracies but also significantly improves privacy preservation, surpassing existing methods in practical applications. This balance between privacy and performance underscores the potential of localized federated updates as a key component in future FL privacy strategies, offering a scalable and effective solution to one of the most pressing challenges in FL.

Funder

Science and Technology Research Planning Project of the Jilin Provincial Department of Education in China

Publisher

MDPI AG

Reference52 articles.

1. The future of digital health with federated learning;Rieke;NPJ Digit. Med.,2020

2. Federated machine learning: Concept and applications;Yang;ACM Trans. Intell. Syst. Technol. (TIST),2019

3. McMahan, B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B.A. (2017, January 20–22). Communication-efficient learning of deep networks from decentralized data. Proceedings of the Artificial Intelligence and Statistics, PMLR, Fort Lauderdale, FL, USA.

4. Xiao, P., Cheng, S., Stankovic, V., and Vukobratovic, D. (2020). Averaging is probably not the optimum way of aggregating parameters in federated learning. Entropy, 22.

5. Vepakomma, P., Gupta, O., Swedish, T., and Raskar, R. (2018). Split learning for health: Distributed deep learning without sharing raw patient data. arXiv.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3