基于零集中差分隐私的联邦学习激励方案

李梦倩; 田有亮; 张军鹏; 赵冬梅

doi:10.11959/j.issn.1000-436x.2025008

您当前的位置：

首页 >

文章列表页 >

基于零集中差分隐私的联邦学习激励方案

学术论文 | 更新时间：2025-02-13

- 基于零集中差分隐私的联邦学习激励方案
- Incentive scheme for federated learning based on zero-concentrated differential privacy
- 通信学报 2025年46卷第1期页码：79-92
- 作者机构：
  
  1.贵州大学公共大数据国家重点实验室，贵州贵阳 550025
  2.贵州大学计算机科学与技术学院，贵州贵阳 550025
  3.贵州大学大数据与信息工程学院，贵州贵阳 550025
  4.河北师范大学河北省网络与信息安全重点实验室，河北石家庄 050024
- 作者简介：
  
  [ "李梦倩（1997- ），女，河北衡水人，贵州大学博士生，主要研究方向为联邦学习、隐私保护、差分隐私技术等。" ]
  [ "田有亮（1982- ），男，贵州盘州人，博士，贵州大学教授、博士生导师，主要研究方向为博弈论、密码学与安全协议、大数据隐私保护。" ]
  [ "张军鹏（1982- ），男，河北石家庄人，河北师范大学副教授，主要研究方向为数据安全、隐私保护、差分隐私技术。" ]
  [ "赵冬梅（1966- ），女，河北深州人，博士，河北师范大学教授、博士生导师，主要研究方向为网络安全主动防御、风险监测、大数据隐私保护。" ]
- 基金信息：
  
  国家自然科学基金资助项目(62272123;61672206;62062020);中央引导地方科技发展基金资助项目(236Z0104G);河北省科技计划基金资助项目(22567606H);贵州省高层次创新型人才基金资助项目;Project of High-level Innovative Talents of Guizhou Province([2020]6008);贵州省科技计划基金资助项目（No.[2020]5017, No.[2022]065）
- DOI：10.11959/j.issn.1000-436x.2025008
  中图分类号： TN92
- 收稿：2024-09-14，
  
  修回：2024-12-11，
  
  纸质出版：2025-01-25
- 稿件说明：
移动端阅览
李梦倩,田有亮,张军鹏等.基于零集中差分隐私的联邦学习激励方案[J].通信学报,2025,46(01):79-92.

LI Mengqian,TIAN Youliang,ZHANG Junpeng,et al.Incentive scheme for federated learning based on zero-concentrated differential privacy[J].Journal on Communications,2025,46(01):79-92.
李梦倩,田有亮,张军鹏等.基于零集中差分隐私的联邦学习激励方案[J].通信学报,2025,46(01):79-92. DOI： 10.11959/j.issn.1000-436x.2025008.

LI Mengqian,TIAN Youliang,ZHANG Junpeng,et al.Incentive scheme for federated learning based on zero-concentrated differential privacy[J].Journal on Communications,2025,46(01):79-92. DOI： 10.11959/j.issn.1000-436x.2025008.

摘要

针对联邦学习场景下客户端选择不公平及模型训练低效问题，提出了一种基于激励机制的隐私保护联邦学习框架（zCDP-FL）。该框架将第二价反向拍卖应用到客户端的选择策略，设计了激励机制算法（SRAI），最大化系统效益。此外，采用零集中差分隐私，提出了隐私预算动态分配算法，实现训练过程中噪声规模的动态调整，在严格隐私计算边界的情况下提供更强的隐私保护。理论分析与仿真实验证明，zCDP-FL能够有效防止隐私泄露，并提升了2.13%~3.62%模型训练效率。

Abstract

To solve problems of unfair client selection and inefficient model training in federated learning

a privacy-preserving federated learning framework was proposed based on the incentive mechanism named zCDP-FL. An incentive mechanism algorithm

SRAI

was designed to maximize system benefits by applying the second price and the reverse auction to the client's selection strategy. In addition

a dynamic allocation algorithm for the privacy budget was proposed based on the zero-concentrated differential privacy to realize the dynamic adjustment of noise scale during the training

which provided a stronger privacy guarantee under the strict privacy constraint. Theoretical analyses and simulation experiments demonstrate that zCDP-FL can effectively prevent privacy leakage and enhance 2.13%~3.62% model training efficiency.

关键词

Keywords

references

AHMED I , JEON G , PICCIALLI F . From artificial intelligence to explainable artificial intelligence in industry 4.0: a survey on what, how, and where [J ] . IEEE Transactions on Industrial Informatics , 2022 , 18 ( 8 ): 5031 - 5042 .

MCMAHAN H B , MOORE E , RAMAGE D , et al . Communication-efficient learning of deep networks from decentralized data [J ] . arXiv Preprint , arXiv: 1602.05629 , 2016 .

MOTHUKURI V , PARIZI R M , POURIYEH S , et al . A survey on security and privacy of federated learning [J ] . Future Generation Computer Systems , 2021 , 115 : 619 - 640 .

WEI K , LI J , DING M , et al . Federated learning with differential privacy: algorithms and performance analysis [J ] . IEEE Transactions on Information Forensics and Security , 2020 , 15 : 3454 - 3469 .

ZHU L G , LIU Z J , HAN S . Deep leakage from gradients [C ] // The 33rd International Conference on Neural Information Processing Systems . Massachusetts : MIT Press , 2019 : 14774 - 14784 .

汤凌韬 , 陈左宁 , 张鲁飞 , 等 . 联邦学习中的隐私问题研究进展 [J ] . 软件学报 , 2023 , 34 ( 1 ): 197 - 229 .

TANG L T , CHEN Z N , ZHANG L F , et al . Research progress of privacy issues in federated learning [J ] . Journal of Software , 2023 , 34 ( 1 ): 197 - 229 .

ZHAO C , ZHAO S N , ZHAO M H , et al . Secure multi-party computation: theory, practice and applications [J ] . Information Sciences , 2019 , 476 : 357 - 372 .

PAILLIER P . Public-key cryptosystems based on composite degree residuosity classes [C ] // International Conference on the Theory and Applications of Cryptographic Techniques . Berlin : Springer , 2007 : 223 - 238 .

李尤慧子 , 殷昱煜 , 高洪皓 , 等 . 面向隐私保护的非聚合式数据共享综述 [J ] . 通信学报 , 2021 , 42 ( 6 ): 195 - 212 .

LI Y H Z , YIN Y Y , GAO H H , et al . Survey on privacy protection in non-aggregated data sharing [J ] . Journal on Communications , 2021 , 42 ( 6 ): 195 - 212 .

RABIN M O . How to exchange secrets with oblivious transfer [J ] . IACR Cryptology EPrint Archive , 2005 , 2005 : 187 .

BELLARE M , HOANG V T , ROGAWAY P . Foundations of garbled circuits [C ] // Proceedings of the 2012 ACM Conference on Computer and Communications Security . New York : ACM Press , 2012 : 784 - 796 .

KARNIN E , GREENE J , HELLMAN M . On secret sharing systems [J ] . IEEE Transactions on Information Theory , 1983 , 29 ( 1 ): 35 - 41 .

DWORK C . Differential privacy: a survey of results [C ] // International Conference on Theory and Applications of Models of Computation . Berlin : Springer , 2008 : 1 - 19 .

KANG J W , XIONG Z H , NIYATO D , et al . Incentive mechanism for reliable federated learning: a joint optimization approach to combining reputation and contract theory [J ] . IEEE Internet of Things Journal , 2019 , 6 ( 6 ): 10700 - 10714 .

DENG Y H , LYU F , REN J , et al . FAIR: quality-aware federated learning with precise user incentive and model aggregation [C ] // Proceedings of the IEEE INFOCOM 2021-IEEE Conference on Computer Communications . Piscataway : IEEE Press , 2021 : 1 - 10 .

ZENG R F , ZHANG S X , WANG J Q , et al . FMore: an incentive scheme of multi-dimensional auction for federated learning in MEC [C ] // Proceedings of the 2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS) . Piscataway : IEEE Press , 2020 : 278 - 288 .

JIN H M , SU L , CHEN D Y , et al . Quality of information aware incentive mechanisms for mobile crowd sensing systems [C ] // Proceedings of the 16th ACM International Symposium on Mobile Ad Hoc Networking and Computing . New York : ACM Press , 2015 : 167 - 176 .

田有亮 , 吴柿红 , 李沓 , 等 . 基于激励机制的联邦学习优化算法 [J ] . 通信学报 , 2023 , 44 ( 5 ): 169 - 180 .

TIAN Y L , WU S H , LI T , et al . Federated learning optimization algorithm based on incentive mechanism [J ] . Journal on Communications , 2023 , 44 ( 5 ): 169 - 180 .

ZHANG L F , ZHU T Q , XIONG P , et al . A robust game-theoretical federated learning framework with joint differential privacy [J ] . IEEE Transactions on Knowledge and Data Engineering , 2023 , 35 ( 4 ): 3333 - 3346 .

CHEN Y R , ZHANG Y Y , WANG S W , et al . DIM-DS: dynamic incentive model for data sharing in federated learning based on smart contracts and evolutionary game theory [J ] . IEEE Internet of Things Journal , 2022 , 9 ( 23 ): 24572 - 24584 .

ZHANG J W , WU Y Z , PAN R . Incentive mechanism for horizontal federated learning based on reputation and reverse auction [C ] // Proceedings of the Web Conference 2021 . New York : ACM Press , 2021 : 947 - 956 .

GUPTA R , GUPTA J . Federated learning using game strategies: state-of-the-art and future trends [J ] . Computer Networks , 2023 , 225 : 109650 .

WEI K , LI J , MA C , et al . Personalized federated learning with differential privacy and convergence guarantee [J ] . IEEE Transactions on Information Forensics and Security , 2023 , 18 : 4488 - 4503 .

ABADI M , CHU A , GOODFELLOW I , et al . Deep learning with differential privacy [C ] // Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security . New York : ACM Press , 2016 : 308 - 318 .

LIU X Y , LI H W , XU G W , et al . PADL: privacy-aware and asynchronous deep learning for IoT applications [J ] . IEEE Internet of Things Journal , 2020 , 7 ( 8 ): 6955 - 6969 .

ZHU L H , LIU X Y , LI Y M , et al . A fine-grained differentially private federated learning against leakage from gradients [J ] . IEEE Internet of Things Journal , 2022 , 9 ( 13 ): 11500 - 11512 .

TRUEX S , LIU L , CHOW K H , et al . LDP-Fed: federated learning with local differential privacy [C ] // Proceedings of the Third ACM International Workshop on Edge Systems, Analytics and Networking . New York : ACM Press , 2020 : 61 - 66 .

LEE J , KIFER D . Concentrated differentially private gradient descent with adaptive per-iteration privacy budget [C ] // Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining . New York : ACM Press , 2018 : 1656 - 1665 .

BUN M , STEINKE T . Concentrated differential privacy: simplifications, extensions, and lower bounds [C ] // Theory of Cryptography Conference . Berlin : Springer , 2016 : 635 - 658 .

康海燕 , 冀源蕊 . 基于本地化差分隐私的联邦学习方法研究 [J ] . 通信学报 , 2022 , 43 ( 10 ): 94 - 105 .

KANG H Y , JI Y R . Research on federated learning approach based on local differential privacy [J ] . Journal on Communications , 2022 , 43 ( 10 ): 94 - 105 .

LU R H , ZHANG W Z , WANG Y , et al . Auction-based cluster federated learning in mobile edge computing systems [J ] . IEEE Transactions on Parallel and Distributed Systems , 2023 , 34 ( 4 ): 1145 - 1158 .

浏览量

1047

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于激励机制的联邦学习优化算法

面向动态算力节点的联邦学习差分隐私重校准方法

HFLGuard：基于聚类和自编码器的异构联邦中毒防御方法

基于多方计算的安全拜占庭弹性联邦学习

空天地一体化网络中基于联邦深度强化学习的边缘协作缓存策略