混洗差分隐私研究综述

张啸剑; 王浩锋; 傅继彬

doi:10.12263/DZXB.20250017

您当前的位置：

首页 >

文章列表页 >

混洗差分隐私研究综述

综述评论 | 更新时间：2026-04-24

- 混洗差分隐私研究综述
- A Survey on Shuffled Differential Privacy
- 电子学报 2025年53卷第12期页码：4787-4810
- 作者机构：
  
  1.河南财经政法大学计算机与信息工程学院，河南郑州 450046
  2.河南省物联大数据处理与安全工程技术研究中心，河南郑州 450121
- 作者简介：
  
  [ "张啸剑男，1980年9月出生于河南省周口市.现为河南财经政法大学计算机与信息工程学院教授、硕士生导师.主要研究方向为数据安全与隐私、差分隐私、数据库，以及图数据管理等.中国电子学会会员编号：E190087355M.E-mail: xjzhang82@alu.ruc.edu.cn" ]
  [ "王浩锋男，1999年9月出生于河南省许昌市.现为河南财经政法大学计算机与信息工程学院硕士研究生.主要研究方向为数据安全与隐私、差分隐私.E-mail: 13140075039@163.com" ]
  [ "傅继彬男，1975年9月出生于河南省许昌市. 现为河南财经政法大学计算机与信息工程学院副教授、硕士生导师.主要研究方向为机器学习、数据安全与隐私保护.E-mail: fujibin@huel.edu.cn" ]
- 基金信息：
  
  国家自然科学基金(62072156);河南省高等学校重点科研项目计划基础研究专项(25ZX012);河南省自然科学杰出青年基金(252300421061)
- DOI：10.12263/DZXB.20250017
  中图分类号： TP309.2;
- 收稿：2025-01-03，
  
  录用：2025-03-24，
  
  纸质出版：2025-12-25
- 稿件说明：
移动端阅览
张啸剑, 王浩锋, 傅继彬. 混洗差分隐私研究综述[J]. 电子学报, 2025, 53(12): 4787-4810.

ZHANG Xiao-jian, WANG Hao-feng, FU Ji-bin. A Survey on Shuffled Differential Privacy[J]. Acta Electronica Sinica, 2025, 53(12): 4787-4810.
张啸剑, 王浩锋, 傅继彬. 混洗差分隐私研究综述[J]. 电子学报, 2025, 53(12): 4787-4810. DOI：10.12263/DZXB.20250017

ZHANG Xiao-jian, WANG Hao-feng, FU Ji-bin. A Survey on Shuffled Differential Privacy[J]. Acta Electronica Sinica, 2025, 53(12): 4787-4810. DOI：10.12263/DZXB.20250017

摘要

基于中心化差分隐私（Central Differential Privacy，CDP）与本地化差分隐私（Local Differential Privacy，LDP）的数据查询和分析已得到了研究者的广泛关注.数据查询与分析的解决方法在CDP/LDP下取得不断突破的同时也凸显出相应的局限性，其局限性源自CDP/LDP是针对收集者信任度变化而设置的两个极端模型.CDP假设用户完全信任收集者，收集者结合用户的原始数据产生噪声来响应分析者的查询，响应的误差较低.然而，该模型中的用户无法掌控自己的原始隐私数据.LDP假设用户不信任收集者，用户只是把本地扰动结果传输给收集者.然而，该模型下查询与分析的误差很高.混洗差分隐私（Shuffled Differential Privacy，SDP）模型的出现有效均衡了CDP与LDP之间的矛盾.本文对SDP的保护模型、实现机制、研究方向以及存在的问题进行系统地综述.首先介绍SDP的理论基础，主要包括SDP模型、SDP框架以及满足SDP算法的核心思想.重点介绍当前该领域的研究热点：聚集查询估计、直方图估计、频率/均值估计以及机器/联邦学习等，对相应的研究热点进行总结与归纳.在对已有技术深入对比分析的基础上，指出了混洗差分隐私保护技术的未来发展方向.

Abstract

Query and analysis of users’ data with centralized differential privacy (CDP) and local differential privacy (LDP) have attracted considerable attention in recent years. The solutions to this problem have been proposed constantly

and the corresponding limitations are also highlighted

which originate from the fact that CDP and LDP are the two extreme models with the changing for collector’s trust. In the CDP model

users fully trust the collector

and report their raw data. The collector perturbs the raw data to respond to the query

which error is low. Users in the CDP model

however

cannot control their raw private data. While

in the LDP model

users do not trust the collector and only report the noise data. The query error over the noise reports is high. The shuffled differential privacy (SDP) model effectively balances the contradiction between CDP and LDP. This paper surveys the state of the art of SDP for data query and analysis. The mechanisms and properties of this model are described

while our focus is put on summation query

histogram estimation

frequency and means estimation

and machine /federated learning

etc. Following the comprehensive comparison and analysis of existing works

future research directions are put forward.

关键词

Keywords

references

DWORK C , MCSHERRY F , NISSIM K , et al . Calibrating noise to sensitivity in private data analysis [C ] // Theory of Cryptography , Third Theory of Cryptography Conference . Heidelberg, Berlin : Springer , 2006 : 265 - 284 .

BEIMEL A , NISSIM K , OMRI E . Distributed private data analysis: Simultaneously solving how and what [M ] // Advances in Cryptology - CRYPTO 2008 . Berlin, Heidelberg : Springer , 2008 : 451 - 468 .

CHAN H H T , SHI E , SONG D . Optimal lower bound for differentially private multi-party aggregation [C ] // 20th Annual European Symposium on Algorithms . Cham : Springer , 2012 : 277 - 288 .

BALLE B , BELL J , CASCÓN A , et al . The privacy blanket of the shuffle model [C ] // 39th Annual International Cryptology Conference . Cham : Springer , 2019 : 638 - 667 .

KAIROUZ P , BONAWITZ K , RAMAGE D . Discrete distribution estimation under local privacy [C ] // Proceedings of the 33rd International Conference on Machine Learning - Volume 48 . New York : ACM , 2016 : 2436 - 2444 .

LUO Q Y , WANG Y L , YI K . Frequency estimation in the shuffle model with almost a single message [C ] // Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security . New York : ACM , 2022 : 2219 - 2232 .

DWORK C , ROTH A . The alogorithmic foundations of differential privacy [J ] . Foundations and Trends in Theoretical Computer Science , 2014 , 9 ( 3/4 ): 211 - 407 .

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

GOTZ M , MACHANAVAJJHALA A , WANG G Z , et al . Publishing search logs: A comparative study of privacy guarantees [J ] . IEEE Transactions on Knowledge and Data Engineering , 2011 , 24 ( 3 ): 520 - 532 .

CORMODE G , PROCOPIUC C , SRIVASTAVA D , et al . Differentially private spatial decompositions [C ] // Proceedings of the 2012 IEEE 28th International Conference on Data Engineering . New York : ACM , 2012 : 20 - 31 .

KELLARIS G , PAPADOPOULOS S , XIAO X K , et al . Differentially private event sequences over infinite streams [J ] . Proc. VLDB Endow , 2014 , 7 ( 12 ): 1155 - 1166 .

ERLINGSSON Ú , PIHUR V , KOROLOVA A . RAPPOR: Randomized aggregatable privacy-preserving ordinal response [C ] // Proceedings of the 2014 ACM SIGSAC Conference on Computer and Communications Security . New York : ACM , 2014 : 1054 - 1067 .

WANG T H , BLOCKI J , LI N H , et al . Locally differentially private protocols for frequency estimation [C ] // Proceedings of the 26th USENIX Conference on Security Symposium . New York : ACM , 2017 : 729 - 745 .

BASSILY R , SMITH A D . Local, private, efficient protocols for succinct histograms [C ] // Proceedings of the Forty-Seventh Annual ACM on Symposium on Theory of Computing . New York : ACM , 2015 : 127 - 135 .

Differential Privacy Team : Learning with privacy at scale . Apple, December 2017 [EB/OL ] . [ 2025-01-03 ] . https://machinelearning.apple.com/2017/12/06/learning-with-privacy-at-scale.html https://machinelearning.apple.com/2017/12/06/learning-with-privacy-at-scale.html .

CORMODE G , KULKARNI T , SRIVASTAVA D . Marginal release under local differential privacy [C ] // Proceedings of the 2018 International Conference on Management of Data . New York : ACM , 2018 : 131 - 146 .

DUCHI J C , JORDAN M I , WAINWRIGHT M J . Local privacy and statistical minimax rates [C ] // 54th Annual IEEE Symposium on Foundations of Computer Science . Piscataway : IEEE , 2013 : 429 - 438 .

WANG N , XIAO X K , YANG Y , et al . Collecting and analyzing multidimensional data with local differential privacy [C ] // IEEE 35th International Conference on Data Engineering . Piscataway : IEEE , 2019 : 638 - 649 .

BITTAU A , ERLINGSSON Ú , MANIATIS P , et al . Prochlo: Strong privacy for analytics in the crowd [C ] // Proceedings of the 26th Symposium on Operating Systems Principles . New York : ACM , 2017 : 441 - 459 .

MCSHERRY F , TALWAR K . Mechanism design via differential privacy [C ] // 48th Annual IEEE Symposium on Foundations of Computer Science . Piscataway : IEEE , 2007 : 94 - 103 .

MCSHERRY F . Privacy integrated queries: An extensible platform for privacy-preserving data analysis [C ] // Proceedings of the 2009 International Conference on Management of Data . New York : ACM , 2009 : 19 - 30 .

WARNER S L . Randomized response: A survey technique for eliminating evasive answer bias [J ] . Journal of the American Statistical Association , 1965 , 60 ( 309 ): 63 - 69 .

LI C , MIKLAU G , HAY M , et al . The matrix mechanism: Optimizing linear counting queries under differential privacy [J ] . The VLDB Journal , 2015 , 24 ( 6 ): 757 - 781 .

WU X , LI F G , KUMAR A , et al . Bolt-on differential privacy for scalable stochastic gradient descent-based analytics [C ] // Proceedings of the 2017 International Conference on Management of Data . New York : ACM , 2017 : 1307 - 1322 .

LI Z T , WANG T H , LOPUHAÄ-ZWAKENBERG M , et al . Estimating numerical distributions under local differential privacy [C ] // Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data . New York : ACM , 2020 : 621 - 635 .

STEMMER U . Locally private k -means clustering [M ] // Proceedings of the Fourteenth Annual ACM-SIAM Symposium on Discrete Algorithms . Philadelphia, PA : Society for Industrial and Applied Mathematics , 2020 : 548 - 559 .

CHEU A , SMITH A , ULLMAN J , et al . Distributed differential privacy via shuffling [C ] // Advances in Cryptology - EUROCRYPT 2019 . New York : ACM , 2019 : 375 - 403 .

GHAZI B , PAGH R , VELINGKER A . Scalable and differentially private distributed aggregation in the shuffled model [EB/OL ] . ( 2019-12-02 )[ 2025-01-03 ] . https://arxiv.org/abs/1906.08320 https://arxiv.org/abs/1906.08320 .

GHAZI B , MANURANGSI P , PAGH R , et al . Private aggregation from fewer anonymous messages [C ] // 39th Annual International Conference on the Theory and Applications of Cryptographic Techniques . Cham : Springer , 2020 : 798 - 827 .

GIRGIS A M , DATA D , DIGGAVI S N , et al . Shuffled model of federated learning: Privacy, accuracy and communication trade-offs [J ] . IEEE Journal on Selected Areas in Information Theory , 2024 , 2 ( 1 ): 464 - 478 .

CHEN L J , GHAZI B , KUMAR R , et al . On distributed differential privacy and counting distinct elements [C ] // 12th Innovations in Theoretical Computer Science Conference . New York : ACM , 2021 : 56 : 1 - 56 : 18 .

CHEU A , ULLMAN J R . The limits of pan privacy and shuffle privacy for learning and estimation [C ] // 53rd Annual ACM SIGACT Symposium on Theory of Computing . New York : ACM , 2021 : 1081 - 1094 .

NISSIM K , YAN C . The sample complexity of distribution-free parity learning in the robust shuffle model [J ] . Journal of Privacy and Confidentiality , 2022 , 12 ( 2 ). DOI: 10.29012/jpc.805 http://dx.doi.org/10.29012/jpc.805 .

EVANS D , KOLESNIKOV V , ROSULEK M . A pragmatic introduction to secure multi-party computation [J ] . Foundations and Trends in Privacy and Security , 2018 , 2 ( 2/3 ): 70 - 246 .

FRANKLIN M , YUNG M . Communication complexity of secure computation (extended abstract) [C ] // Proceedings of the Twenty-Fourth Annual ACM Symposium on Theory of Computing . New York : ACM , 1992 : 699 - 710 .

PAILLIER P . Public-key cryptosystems based on composite degree residuosity classes [C ] // Advances in Cryptology - EUROCRYPT’99 . Berlin : Springer , 1999 : 223 - 238 .

BALCER V , CHEU A , JOSEPH M , et al . Connecting robust shuffle privacy and pan-privacy [C ] // Proceedings of the 2021 ACM-SIAM Symposium on Discrete Algorithms . New York : ACM , 2021 : 2384 - 2403 .

WANG T H , XU M , DING B L , et al . Practical and robust privacy amplification with multi-party differential privacy [EB/OL ] . ( 2020-08-02 )[ 2025-01-03 ] . https://arxiv.org/abs/1908.11515v1 https://arxiv.org/abs/1908.11515v1 .

WANG T H , DING B L , XU M , et al . Improving utility and security of the shuffler-based differential privacy [J ] . Proceedings of the VLDB Endowment , 2020 , 13 ( 13 ): 3545 - 3558 .

BALCER V , CHEU A . Separating local & shuffled differential privacy via histograms [C ] // 1st Conference on Information-Theoretic Cryptography . Cham : Springer , 2020 . DOI: 10.4230/LIPIcs.ITC.2020.1 http://dx.doi.org/10.4230/LIPIcs.ITC.2020.1 .

ERLINGSSON Ú , FELDMAN V , MIRONOV I , et al . Amplification by shuffling: From local to central differential privacy via anonymity [C ] // Proceedings of the Thirtieth Annual ACM-SIAM Symposium on Discrete Algorithms . Philadelphia, PA : Society for Industrial and Applied Mathematics , 2019 : 2468 - 2479 .

ALLEN J , DING B L , KULKARNI J , et al . An algorithmic framework for differentially private data analysis on trusted processors [C ] // Proceedings of the 33rd International Conference on Neural Information Processing Systems . New York : ACM , 2019 : 13635 - 13646 .

FELDMAN V , MCMILLAN A , TALWAR K . Hiding among the clones: A simple and nearly optimal analysis of privacy amplification by shuffling [C ] // 62nd IEEE Annual Symposium on Foundations of Computer Science . Piscataway : IEEE , 2021 : 954 - 964 .

CHEU A , ZHILYAEV M . Differentially private histograms in the shuffle model from fake users [C ] // 2022 IEEE Symposium on Security and Privacy . Piscataway : IEEE , 2022 : 440 - 457 .

EBERL M . Fisher-yates shuffle [EB/OL ] . ( 2016-10-05 )[ 2025-01-03 ] . https://www.wikiwand.com/en/articles/Fisher%E2%80%93Yates_shuffle https://www.wikiwand.com/en/articles/Fisher%E2%80%93Yates_shuffle .

GHAZI B , GOLOWICH N , KUMAR R , et al . On the power of multiple anonymous messages [EB/OL ] . ( 2020-05-19 )[ 2025-01-03 ] . https://eprint.iacr.org/2019/1382.pdf https://eprint.iacr.org/2019/1382.pdf .

BASSILY R , NISSIM K , STEMMER U , et al . Practical locally private heavy hitters [C ] // Proceedings of the 31st International Conference on Neural Information Processing Systems . New York : ACM , 2017 : 2285 - 2293 .

ACHARYA J , SUN Z T , ZHANG H Y . Hadamard response: Estimating distributions privately, efficiently, and with little communication [C ] // The 22nd International Conference on Artificial Intelligence and Statistics . New York : ACM , 2019 : 1120 - 1129 .

ACHARYA J SUN Z T . Communication complexity in locally private distribution estimation and heavy hitters [C ] // Proceedings of the 36th International Conference on Machine Learning . New York : ACM , 2019 : 51 - 60 .

BALLE B , BELL J , GASCÓN A , et al . Private summation in the multi-message shuffle model [C ] // Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security . New York : ACM , 2020 : 657 - 676 .

BALLE B , BELL J , GASCÓN A , et al . Differentially private summation with multi-message shuffling [EB/OL ] . ( 2019-08-21 )[ 2025-01-03 ] . https://arxiv.org/abs/1906.09116 https://arxiv.org/abs/1906.09116 .

BALLE B , BELL J , GASCÓN A , et al . Improved summation from shuffling [EB/OL ] . ( 2019-09-24 )[ 2025-01-03 ] . https://arxiv.org/abs/1909.11225 https://arxiv.org/abs/1909.11225 .

ERLINGSSON Ú , FELDMAN V , MIRONOV I , et al . Encode, shuffle, analyze privacy revisited: Formalizations and empirical evaluation [EB/OL ] . ( 2019-01-10 )[ 2025-01-03 ] . https://arxiv.org/abs/2001.03618 https://arxiv.org/abs/2001.03618 .

GHAZI B , GOLOWICH N , KUMAR R , et al . Pure differentially private summation from anonymous messages [C ] // 1st Conference on Information-Theoretic Cryptography . Cham : Springer , 2022 . DOI: 10.4230/LIPIcs.ITC.2020.15 http://dx.doi.org/10.4230/LIPIcs.ITC.2020.15 .

GHAZI B KUMAR R , MANURANGSI P , et al . Private counting from anonymous messages: Near-optimal accuracy with vanishing communication overhead [C ] // Proceedings of the 37th International Conference on Machine Learning . New York : ACM , 2020 : 3505 - 3514 .

ISHAI Y , KUSHILEVITZ E , OSTROVSKY R , et al . Cryptography from anonymity [C ] // 2006 47th Annual IEEE Symposium on Foundations of Computer Science . Piscataway : IEEE , 2006 : 239 - 248 .

CHEU A . Differential privacy in the shuffle model: A survey of separations [EB/OL ] . ( 2022-05-24 )[ 2025-01-03 ] . https://arxiv.org/abs/2107.11839 https://arxiv.org/abs/2107.11839 .

XU S Q , ZHENG Y F , HUA Z Y . Camel: Communication-efficient and maliciously secure federated learning in the shuffle model of differential privacy [C ] // Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security . New York : ACM , 2024 : 243 - 257 .

GHAZI B , KUMAR R , MANURANGSI P , et al . Differentially private aggregation in the shuffle model: Almost central accuracy in almost a single message [C ] // Proceedings of the 39th International Conference on Machine Learning . New York : ACM , 2023 : 3692 - 3701 .

GHAZI B , GOLOWICH N , KUMAR R , et al . On the power of multiple anonymous messages: Frequency estimation andSelection in the shuffle model of Differential privacy [C ] // Advances in Cryptology - EUROCRYPT 2021 . Cham : Springer , 2021 : 463 - 488 .

GORMODE G , MUTHUKRISHNAN S . An improved data stream summary: The count-min sketch and its applications [J ] . Journal of Algorithms , 2005 , 55 ( 1 ): 58 - 75 .

LI X C , LIU W R , CHEN Z Y , et al . DUMP: A dummy-point-based framework for histogram estimation in shuffle model [EB/OL ] . ( 2021-07-31 )[ 2025-01-03 ] . https://arxiv.org/abs/2009.13738v1 https://arxiv.org/abs/2009.13738v1 .

VADHAN S . The complexity of differential privacy [M ] // Tutorials on the Foundations of Cryptography: Dedicated to Oded Goldreich . Cham : Springer International Publishing , 2017 : 347 - 450 .

BOTTOU L . Large-scale machine learning with stochastic gradient descent [C ] // Proceedings of COMPSTAT’2010 . Heidelberg : Springer , 2010 : 177 - 186 .

CHAUDHURI K , MONTELEONI C , SARWATE A D . Differentially private empirical risk minimization [J ] . Journal of Machine Learning Research , 2011 , 12 : 1069 - 1109 .

BASSILY R , SMITH A , THAKURTA A . Private empirical risk minimization: Efficient algorithms and tight error bounds [C ] // 2014 IEEE 55th Annual Symposium on Foundations of Computer Science . Piscataway : IEEE , 2014 : 464 - 473 .

AGARWAL N , SURESH A T , YU F X , et al . CpSGD: Communication-efficient and differentially-private distributed SGD [C ] // Proceedings of the 32nd International Conference on Neural Information Processing Systems . New York : ACM , 2018 : 7575 - 7586 .

SURESH A T , YU F X , SANJIV K H , et al . Distributed mean estimation with limited communication [C ] // Proceedings of the 34th International Conference on Machine Learning . New York : ACM , 2017 : 3329 - 3337 .

MCMAHAN H B , RAMAGE D , TALWAR K , et al . Learning differentially private recurrent language models [C ] // International Conference on Learning Representations . ICLR , 2017 . https://openreview.net/forum?id=BJ0hF1Z0b https://openreview.net/forum?id=BJ0hF1Z0b .

LOWY A , RAZAVIYAYN M . Locally differentially private federated learning: Efficient algorithms with tight risk bounds [EB/OL ] . ( 2024-11-24 )[ 2025-01-03 ] . https://arxiv.org/abs/2106.09779v1 https://arxiv.org/abs/2106.09779v1 .

DUCHI J C , JORDAN M I , WAINWRIGHT M J . Minimax optimal procedures for locally private estimation [J ] . Journal of the American Statistical Association , 2018 , 113 ( 521 ): 182 - 201 .

YANG Q , LIU Y , CHEN T J , et al . Federated machine learning: Concept and applications [J ] . ACM Transactions on Intelligent Systems and Technology , 2019 , 10 ( 2 ): 1 - 19 .

CHEU A , JOSEPH M , MAO J M , et al . Shuffle private stochastic convex optimization [C ] // 10th International Conference on Learning Representations . New York : ACM , 2022 : 209 .

GIRGIS A M , DATA D , DIGGAVI S N . Rényi differential privacy of the subsampled shuffle model in distributed learning [C ] // Proceedings of the 35th International Conference on Neural Information Processing Systems . New York : ACM , 2021 : 29181 - 29192 .

MIRONOV I . Rényi differential privacy [C ] // 30th IEEE Computer Security Foundations Symposium . Piscataway : IEEE , 2017 : 263 - 275 .

GIRGIS A M , DATA D , DIGGAVI S , et al . On the rényi differential privacy of the shuffle model [C ] // Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security . New York : ACM , 2021 : 2321 - 2341 .

LIEW S P , HASEGAWA S , TAKAHASHI T . Shuffled check-in: Privacy amplification towards practical distributed learning [EB/OL ] . ( 2023-07-04 )[ 2025-01-03 ] . https://arxiv.org/abs/2206.03151v1 https://arxiv.org/abs/2206.03151v1 .

BASSILY R , FELDMAN V , TALWAR K , et al . Private stochastic convex optimization with optimal rates [C ] // Proceedings of the 33rd International Conference on Neural Information Processing Systems . New York : ACM , 2019 : 11279 - 11288 .

ZHU L G , LIU Z J , HAN S . Deep leakage from gradients [C ] // Proceedings of the 33rd International Conference on Neural Information Processing Systems . New York : ACM , 2019 : 14747 - 14756 .

WEI W Q , LIU L . Gradient leakage attack resilient deep learning [J ] . IEEE Transactions on Information Forensics and Security , 2021 , 17 : 303 - 316 .

GEYER R C , KLEIN T , NABI M . Differentially private federated learning: A client level perspective [EB/OL ] . ( 2018-03-01 )[ 2025-01-03 ] https://arxiv.org/abs/1712.07557 https://arxiv.org/abs/1712.07557 .

TRUEX S , LIU L , CHOW K H , et al . LDP-Fed: federated learning with local differential privacy [C ] // Proceedings of the 3rd International Workshop on Edge Systems, Analytics and Networking . New York : ACM , 2020 : 61 - 66 .

WANG L , JIA R X , SONG D . D 2 P-Fed: Differentially private federated learning with efficient communication [EB/OL ] . ( 2021-01-02 )[ 2025-01-03 ] . https://arxiv.org/abs/2006.13039 https://arxiv.org/abs/2006.13039 .

WEI K , LI J , DING M , et al . User-level privacy-preserving federated learning: Analysis and performance optimization [J ] . IEEE Transactions on Mobile Computing , 2022 , 21 ( 9 ): 3388 - 3401 .

ANDREW G , THAKKAR O , MCMAHAN B , et al . Differentially private learning with adaptive clipping [C ] // Proceedings of the 35th International Conference on Neural Information Processing Systems . New York : ACM , 2021 : 17455 - 17466 .

ZHANG X W , CHEN X Y , HONG M Y , et al . Understanding clipping for federated learning: Convergence and client-level differential privacy [C ] // Proceedings of the 39th International Conference on Machine Learning . New York : ACM , 2022 : 26048 - 26067 .

SUN L C , QIAN J W , CHEN X . LDP-FL: Practical private aggregation in federated learning with local differential privacy [C ] // Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence . Cham : Springer , 2021 : 1571 - 1578 .

LIU R X , CAO Y , CHEN H , et al . FLAME: Differentially private federated learning in the shuffle model [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2021 , 35 ( 10 ): 8688 - 8696 .

SCOTT M , CORMODE G , MAPLE C . Aggregation and transformation of vector-valued messages in the shuffle model of differential privacy [J ] . IEEE Transactions on Information Forensics and Security , 2022 , 17 : 612 - 627 .

RASTOGI V , NATH S . Differentially private aggregation of distributed time-series with transformation and encryption [C ] // Proceedings of the 2010 ACM SIGMOD International Conference on Management of data . New York : ACM , 2010 : 735 - 746 .

GIRGIS A , DATA D , DIGGAVI S , et al . Shuffled model of differential privacy in federated learning [C ] // Proceedings of The 24th International Conference on Artificial Intelligence and Statistics . PMLR , 2021 : 2521 - 2529 .

WANG S W , PENG Y , LI J , et al . Privacy amplification via shuffling: Unified, simplified, and tightened [J ] . Proceedings of the VLDB Endowment , 2024 , 17 ( 8 ): 1870 - 1883 .

GIRGIS A M , DATA D , DIGGAVI S . Differentially private federated learning with shuffling and client self-sampling [C ] // 2021 IEEE International Symposium on Information Theory . Piscataway : IEEE , 2021 : 338 - 343 .

FELDMAN V , MCMILLAN A , TALWAR K . Stronger privacy amplification by shuffling for rényi and approximate differential privacy [EB/OL ] . ( 2023-10-30 )[ 2025-01-03 ] . https://arxiv.org/abs/2208.04591 https://arxiv.org/abs/2208.04591 .

CHEN W N , ÖZGÜR A , KAIROUZ P . The poisson binomial mechanism for unbiased federated learning with secure aggregation [C ] // Proceedings of the 41st International Conference on Machine Learning . New York : ACM , 2024 : 3490 - 3506 .

BALLE B , KAIROUZ P , MCMAHAN B , et al . Privacy amplification via random check-ins [C ] // Proceedings of the 34th International Conference on Neural Information Processing Systems . New York : ACM , 2020 : 23 - 31 .

BALLE B , BARTHE G , GABOARDI M . Privacy amplification by subsampling: Tight analyses via couplings and divergences [C ] // Proceedings of the 32nd International Conference on Neural Information Processing Systems . New York : ACM , 2018 : 6280 - 6290 .

CORMODE G , KULKARNI T , SRIVASTAVA D . Answering range queries under local differential privacy [J ] . Proceedings of the VLDB Endowment , 2019 , 12 ( 10 ): 1126 - 1138 .

WANG T H , DING B L , ZHOU J R , et al . Answering multi-dimensional analytical queries under local differential privacy [C ] // Proceedings of the 2019 International Conference on Management of Data . New York : ACM , 2019 : 159 - 176 .

XU M , DING B L , WANG T H , et al . Collecting and analyzing data jointly from multiple services under local differential privacy [J ] . Proceedings of the VLDB Endowment , 2020 , 13 ( 12 ): 2760 - 2772 .

GHAZI B , COLOWICH N , KUMAR R , et al . Private heavy hitters and range queries in the shuffled model [EB/OL ] . ( 2020-08-15 )[ 2025-01-03 ] . https://dblp.org/rec/journals/corr/abs-1908-11358.html https://dblp.org/rec/journals/corr/abs-1908-11358.html .

KARWA V , RASKHODNIKOVA S , SMITH A , et al . Private analysis of graph structure [J ] . Proceedings of the VLDB Endowment , 2011 , 4 ( 11 ): 1146 - 1157 .

DAY W Y , LI N H , LYU M . Publishing graph degree distribution with node differential privacy [C ] // Proceedings of the 2016 International Conference on Management of Data . New York : ACM , 2016 : 123 - 138 .

YE Q Q , HU H B , AU M H , et al . LF-GDPR: A framework for estimating graph metrics with local differential privacy [J ] . IEEE Transactions on Knowledge and Data Engineering , 2022 , 34 ( 10 ): 4905 - 4920 .

IMOLA J , MURAHAMI T , CHAUDHURI K . Locally differentially private analysis of graph statistics [C ] // Proceedings of the 30th USENIX Security Symposium . Berkeley : USENIX , 2021 : 983 - 1000 .

IMOLA J , MURAKAMI T , CHAUDHURI K . Differentially private triangle and 4-cycle counting in the shuffle model [C ] // Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security . New York : ACM , 2022 : 1505 - 1519 .

KAIROUZ P LIU Z Y , STEINKE T . The distributed discrete gaussian mechanism for federated learning with secure aggregation [C ] // Proceedings of the 40th International Conference on Machine Learning . New York : ACM , 2023 : 5201 - 5212 .

AGARWAL N , KAIROUZ P , LIU Z Y . The skellam mechanism for differentially private federated learning [C ] // Proceedings of the 36th International Conference on Neural Information Processing Systems . New York : ACM , 2022 : 5052 - 5064 .

WANG S W , YU S Y , REN X J , et al . Differentially private numerical vector analyses in the local and shuffle model [J ] . IEEE Transactions on Dependable and Secure Computing , 2025 , 22 ( 1 ): 1 - 15 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于敏感组件函数调用图的安卓重打包恶意软件检测方法

基于机器学习的高效率集成电路DFT技术研究

DRHA-UIE：基于双重残差混合注意力模块的水下图像增强方法

认知学习：电磁频谱空间机器学习新范式