Free Privacy Protection for Wireless Federated Learning: Enjoy It or Suffer From It?

IF 8 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS
Weicai Li;Tiejun Lv;Xiyu Zhao;Xin Yuan;Wei Ni
{"title":"Free Privacy Protection for Wireless Federated Learning: Enjoy It or Suffer From It?","authors":"Weicai Li;Tiejun Lv;Xiyu Zhao;Xin Yuan;Wei Ni","doi":"10.1109/TIFS.2025.3581042","DOIUrl":null,"url":null,"abstract":"Inherent communication noises have the potential to preserve privacy for wireless federated learning (WFL) but have been overlooked in digital communication systems predominantly using floating-point number standards, e.g., IEEE 754, for data storage and transmission. This is due to the potentially catastrophic consequences of bit errors in floating-point numbers, e.g., on the sign or exponent bits. This paper presents a novel channel-native bit-flipping differential privacy (DP) mechanism tailored for WFL, where transmit bits are randomly flipped and communication noises are leveraged, to collectively preserve the privacy of WFL in digital communication systems. The key idea is to interpret the bit perturbation at the transmitter and bit errors caused by communication noises as a bit-flipping DP process. This is achieved by designing a new floating-point-to-fixed-point conversion method that only transmits the bits in the fraction part of model parameters, hence eliminating the need for transmitting the sign and exponent bits and preventing the catastrophic consequence of bit errors. We analyze a new metric to measure the bit-level distance of the model parameters and prove that the proposed mechanism satisfies <inline-formula> <tex-math>$(\\lambda,\\epsilon)$ </tex-math></inline-formula>-Rényi DP and does not violate the WFL convergence. Experiments validate privacy and convergence analysis of the proposed mechanism and demonstrate its superiority to the state-of-the-art Gaussian mechanisms that are channel-agnostic and add Gaussian noise for privacy protection.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"20 ","pages":"6263-6278"},"PeriodicalIF":8.0000,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Information Forensics and Security","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/11040056/","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, THEORY & METHODS","Score":null,"Total":0}
引用次数: 0

Abstract

Inherent communication noises have the potential to preserve privacy for wireless federated learning (WFL) but have been overlooked in digital communication systems predominantly using floating-point number standards, e.g., IEEE 754, for data storage and transmission. This is due to the potentially catastrophic consequences of bit errors in floating-point numbers, e.g., on the sign or exponent bits. This paper presents a novel channel-native bit-flipping differential privacy (DP) mechanism tailored for WFL, where transmit bits are randomly flipped and communication noises are leveraged, to collectively preserve the privacy of WFL in digital communication systems. The key idea is to interpret the bit perturbation at the transmitter and bit errors caused by communication noises as a bit-flipping DP process. This is achieved by designing a new floating-point-to-fixed-point conversion method that only transmits the bits in the fraction part of model parameters, hence eliminating the need for transmitting the sign and exponent bits and preventing the catastrophic consequence of bit errors. We analyze a new metric to measure the bit-level distance of the model parameters and prove that the proposed mechanism satisfies $(\lambda,\epsilon)$ -Rényi DP and does not violate the WFL convergence. Experiments validate privacy and convergence analysis of the proposed mechanism and demonstrate its superiority to the state-of-the-art Gaussian mechanisms that are channel-agnostic and add Gaussian noise for privacy protection.
无线联合学习的免费隐私保护:享受还是遭受?
固有的通信噪声有可能保护无线联邦学习(WFL)的隐私,但在主要使用浮点数标准(例如IEEE 754)进行数据存储和传输的数字通信系统中却被忽视了。这是由于浮点数(例如,符号位或指数位)的位错误可能造成灾难性后果。本文提出了一种针对WFL的信道原生比特翻转差分隐私(DP)机制,该机制通过随机翻转发送位和利用通信噪声来共同保护数字通信系统中WFL的隐私。关键思想是将发射机的位扰动和通信噪声引起的位误差解释为位翻转DP过程。这是通过设计一种新的浮点到定点转换方法来实现的,该方法只传输模型参数的分数部分的比特,从而消除了传输符号和指数比特的需要,防止了误码的灾难性后果。我们分析了一种新的度量来度量模型参数的比特级距离,并证明了所提出的机制满足$(\lambda,\epsilon)$ - r nyi DP并且不违反WFL收敛性。实验验证了所提出机制的隐私性和收敛性分析,并证明了其优于当前最先进的高斯机制,该机制是信道不可知的,并添加高斯噪声来保护隐私。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
IEEE Transactions on Information Forensics and Security
IEEE Transactions on Information Forensics and Security 工程技术-工程:电子与电气
CiteScore
14.40
自引率
7.40%
发文量
234
审稿时长
6.5 months
期刊介绍: The IEEE Transactions on Information Forensics and Security covers the sciences, technologies, and applications relating to information forensics, information security, biometrics, surveillance and systems applications that incorporate these features
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信