Differential Privacy in Federated Learning: Challenges and Prospects

doi:10.3778/j.issn.1673-9418.2504088

Abstract

Abstract: In federated learning, differential privacy serves as a key technology for addressing privacy concerns, yet it still faces multiple challenges in adapting to heterogeneous environments, personalized privacy design, and communication optimization. Focusing on the current research status of differential privacy in federated learning, this paper conducts an in-depth analysis around three typical application scenarios: differential privacy in heterogeneous environments, personalized differential privacy protection, and differential privacy-communication optimization mechanisms. Specifically, this paper explores the design ideas of differential privacy mechanisms under the conditions of statistical heterogeneity, device heterogeneity, and model heterogeneity respectively, and compares the technical paths and evolutionary trends of various methods in terms of perturbation strategies, budget allocation, and adaptation capabilities. On this basis, this paper further summarizes the performance of current differential privacy mechanisms in terms of computational efficiency, communication overhead, and model adaptability, concludes their advantages and disadvantages, and clarifies the applicable scenarios of different mechanisms through the comparison of typical algorithms. To more comprehensively evaluate the actual effects of these mechanisms, this paper also analyzes the impact of differential privacy strategies on model accuracy, communication rounds, and convergence speed in federated learning by combining experimental results, and reveals the trade-off relationship between privacy protection and utility improvement. Finally, based on the limitations of existing research, this paper prospects the joint optimization mechanisms of differential privacy in multi-dimensional heterogeneous and personalized scenarios.

Key words: federated learning, differential privacy, heterogeneous environments, personalized differential privacy, privacy-communication trade-off

摘要： 在联邦学习中，差分隐私是应对隐私问题的关键技术，但差分隐私在联邦学习的异构环境适应、个性化隐私设计及通信优化等方面仍面临诸多问题。针对联邦学习中差分隐私的研究现状，围绕三类典型应用场景——异构环境下的差分隐私、个性化差分隐私保护以及差分隐私-通信优化机制，展开深入分析。分别探讨统计异构、设备异构与模型异构条件下差分隐私机制的设计思路，比较各类方法在扰动策略、预算分配与适配能力等方面的技术路径及演化趋势。在此基础上，进一步总结当前差分隐私机制在计算效率、通信开销及模型适应性方面的性能表现，归纳其优势与不足，并通过典型算法对比明确不同机制的适用场景。为了更全面评估这些机制的实际效果，还结合实验结果分析差分隐私策略在联邦学习中对模型精度、通信轮次与收敛速度的影响，揭示其在保护隐私与提升效用之间的权衡关系。基于现有研究的不足，展望差分隐私在多维异构与个性化场景下的联合优化机制。

关键词: 联邦学习, 差分隐私, 异构环境, 个性化差分隐私, 隐私-通信权衡

LIU Yi, JIANG Chengjie, YANG Songtao, ZHANG Lei, WU Shiwei. Differential Privacy in Federated Learning: Challenges and Prospects[J]. Journal of Frontiers of Computer Science and Technology, 2025, 19(12): 3179-3201.

刘义, 蒋澄杰, 杨松涛, 张磊, 吴世伟. 联邦学习中的差分隐私现状：机遇与挑战[J]. 计算机科学与探索, 2025, 19(12): 3179-3201.

References

[1] NILSSON A, SMITH S, ULM G, et al. A performance evaluation of federated learning algorithms[C]//Proceedings of the 2nd Workshop on Distributed Infrastructures for Deep Learning. New York: ACM, 2018: 1-8.
[2] 段昕汝, 陈桂茸, 陈爱网, 等. 联邦学习中的信息安全问题研究综述[J]. 计算机工程与应用, 2024, 60(3): 61-77.
DUAN X R, CHEN G R, CHEN A W, et al. Review of research on information security in federated learning[J]. Computer Engineering and Applications, 2024, 60(3): 61-77.
[3] BANABILAH S, ALOQAILY M, ALSAYED E, et al. Federated learning review: fundamentals, enabling technologies, and future applications[J]. Information Processing & Management, 2022, 59(6): 103061.
[4] ALAZAB M, RM S P, PARIMALA M, et al. Federated learning for cybersecurity: concepts, challenges, and future directions[J]. IEEE Transactions on Industrial Informatics, 2022, 18(5): 3501-3509.
[5] LIU P R, XU X R, WANG W. Threats, attacks and defenses to federated learning: issues, taxonomy and perspectives[J]. Cybersecurity, 2022, 5(1): 4.
[6] DWORK C. Differential privacy[C]//Proceedings of the 2006 International Colloquium on Automata, Languages, and Progra-mming. Berlin, Heidelberg: Springer, 2006: 1-12.
[7] 冯晗, 伊华伟, 李晓会, 等. 推荐系统的隐私保护研究综述[J]. 计算机科学与探索, 2023, 17(8): 1814-1832.
FENG H, YI H W, LI X H, et al. Review of privacy-preserving research in recommendation systems[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(8): 1814-1832.
[8] MIRONOV I, PANDEY O, REINGOLD O, et al. Computational differential privacy[C]//Proceedings of the Annual International Cryptology Conference. Berlin, Heidelberg: Sprin-ger, 2009: 126-142.
[9] 康健, 吴英杰, 黄泗勇, 等. 异方差加噪下的差分隐私直方图发布算法[J]. 计算机科学与探索, 2016, 10(6): 786-798.
KANG J, WU Y J, HUANG S Y, et al. Algorithm for differential privacy histogram publication with non-uniform private budget[J]. Journal of Frontiers of Computer Science and Technology, 2016, 10(6): 786-798.
[10] FUKAMI T, MURATA T, NIWA K, et al. DP-norm: differential privacy primal-dual algorithm for decentralized federated learning[J]. IEEE Transactions on Information Forensics and Security, 2024, 19: 5783-5797.
[11] LIU J, LOU J, XIONG L, et al. Cross-silo federated learning with record-level personalized differential privacy[C]//Proceedings of the 2024 ACM SIGSAC Conference on Computer and Communications Security. New York: ACM, 2024: 303-317.
[12] XU Z, ZHANG Y X, ANDREW G, et al. Federated learning of gboard language models with differential privacy[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2023: 629-639.
[13] YANG X, HUANG W, YE M. Dynamic personalized federated learning with adaptive differential privacy[C]//Proceedings of the 37th International Conference on Neural Information Processing Systems, 2023: 72181-72192.
[14] EL OUADRHIRI A, ABDELHADI A. Differential privacy for deep and federated learning: a survey[J]. IEEE access, 2022, 10: 22359-22380.
[15] FU J, HONG Y, LING X, et al. Differentially private federated learning: a systematic review[EB/OL]. [2025-02-17]. https://arxiv.org/abs/2405.08299.
[16] GAO D S, YAO X, YANG Q. A survey on heterogeneous federated learning[EB/OL]. [2025-02-17]. https://arxiv.org/abs/2210.04505.
[17] LUO B, LI X, WANG S Q, et al. Cost-effective federated learning design[C]//Proceedings of the 2021 IEEE Conference on Computer Communications. Piscataway: IEEE, 2021: 1-10.
[18] ZENG D, LIANG S Q, HU X J, et al. FedLab: a flexible federated learning framework[EB/OL]. [2025-02-17]. https://arxiv.org/abs/2107.11621.
[19] DWORK C, ROTHBLUM G N, VADHAN S. Boosting and differential privacy[C]//Proceedings of the 51st Annual IEEE Symposium on Foundations of Computer Science. Piscataway: IEEE, 2010: 51-60.
[20] 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.
[21] HUANG W K, YE M, DU B. Learn from others and be yourself in heterogeneous federated learning[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 10133-10143.
[22] QIN Z, DENG S, ZHAO M, et al. FedAPEN: personalized cross-silo federated learning with adaptability to statistical heterogeneity[C]//Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York: ACM, 2023: 1954-1964.
[23] WANG S, LEE M Y, HOSSEINALIPOUR S, et al. Device sampling for heterogeneous federated learning: theory, algorithms, and implementation[C]//Proceedings of the 2021 IEEE Conference on Computer Communications. Piscataway: IEEE, 2021: 1-10.
[24] ZHANG C, XIE Y, BAI H, et al. A survey on federated learning[J]. Knowledge-Based Systems, 2021, 216: 106775.
[25] AMIRI S, BELLOUM A, NALISNICK E, et al. On the impact of non-IID data on the performance and fairness of differentially private federated learning[C]//Proceedings of the 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks. Piscataway: IEEE, 2022: 52-58.
[26] XIONG Z B, CAI Z P, TAKABI D, et al. Privacy threat and defense for federated learning with non-i.i.d. data in AIoT[J]. IEEE Transactions on Industrial Informatics, 2022, 18(2): 1310-1321.
[27] YANG X Y, WU W S. A federated learning differential privacy algorithm for non-Gaussian heterogeneous data[J]. Scientific Reports, 2023, 13: 5819.
[28] 汤凌韬, 王迪, 刘盛云. 面向非独立同分布数据的联邦学习数据增强方案[J]. 通信学报, 2023, 44(1): 164-176.
TANG L T, WANG D, LIU S Y. Data augmentation scheme for federated learning with non-IID data[J]. Journal on Communications, 2023, 44(1): 164-176.
[29] WENG S Y, ZHANG L, FENG D Q, et al. Privacy-preserving federated learning based on differential privacy and momentum gradient descent[C]//Proceedings of the 2022 International Joint Conference on Neural Networks. Piscataway: IEEE, 2022: 1-6.
[30] NOBLE M, BELLET A, DIEULEVEUT A. Differentially private federated learning on heterogeneous data[C]//Proceedings of the 2022 International Conference on Artificial Intelligence and Statistics, 2022: 10110-10145.
[31] WANG C, WU X K, LIU G Y, et al. Safeguarding cross-silo federated learning with local differential privacy[J]. Digital Communications and Networks, 2022, 8(4): 446-454.
[32] 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.
[33] TRIASTCYN A, FALTINGS B. Federated learning with Bayesian differential privacy[C]//Proceedings of the 2019 IEEE International Conference on Big Data. Piscataway: IEEE, 2019: 2587-2596.
[34] LIU B, BLANCAFLOR E B, FANG T K, et al. Privacy protection based on federated learning[J]. Journal of Artificial Intelligence and Technology, 2025, 5: 10-19.
[35] SHI Y J, LIANG J, ZHANG W Q, et al. Towards understanding and mitigating dimensional collapse in heterogeneous federated learning[EB/OL]. [2025-02-17]. https://arxiv.org/abs/2210.00226.
[36] BOENISCH F, DZIEDZIC A, SCHUSTER R, et al. Reconstructing individual data points in federated learning hardened with differential privacy and secure aggregation[C]//Proceedings of the 8th IEEE European Symposium on Security and Privacy. Piscataway: IEEE, 2023: 241-257.
[37] MALEKMOHAMMADI S, YU Y L, CAO Y. Noise-aware algorithm for heterogeneous differentially private federated learning[C]//Proceedings of the 41st International Conference on Machine Learning, 2024: 34461-34498.
[38] TRUEX S, LIU L, CHOW K H, et al. LDP-Fed: federated learning with local differential privacy[C]//Proceedings of the 3rd ACM International Workshop on Edge Systems, Analy-tics and Networking. New York: ACM, 2020: 61-66.
[39] CHEN S Z, YU D X, ZOU Y F, et al. Decentralized wireless federated learning with differential privacy[J]. IEEE Transactions on Industrial Informatics, 2022, 18(9): 6273-6282.
[40] SO J, ALI R E, GüLER B, et al. Securing secure aggregation: mitigating multi-round privacy leakage in federated learning[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2023, 37(8): 9864-9873.
[41] XU X H, DUAN S J, ZHANG J R, et al. Optimizing federated learning on device heterogeneity with a sampling strategy[C]//Proceedings of the 2021 IEEE/ACM 29th International Symposium on Quality of Service. Piscataway: IEEE, 2021: 1-10.
[42] JUNG K, BAEK I, KIM S, et al. LAFD: local-differentially private and asynchronous federated learning with direct feedback alignment[J]. IEEE Access, 2023, 11: 86754-86769.
[43] 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.
[44] LI M C, TIAN Y, FENG Y, et al. Federated transfer learning with differential privacy[EB/OL]. [2025-02-18]. https://arxiv.org/abs/2403.11343.
[45] PAN Y H, NI J B, SU Z. FL-PATE: differentially private federated learning with knowledge transfer[C]//Proceedings of the 2021 IEEE Global Communications Conference. Piscataway: IEEE, 2021: 1-6.
[46] QI T, WU F Z, WU C H, et al. Differentially private knowledge transfer for federated learning[J]. Nature Communications, 2023, 14: 3785.
[47] SUN L C, LYU L J. Federated model distillation with noise-free differential privacy[EB/OL]. [2025-02-18]. https://arxiv.org/abs/2009.05537.
[48] WANG F, GURSOY M C, VELIPASALAR S. Feature-based federated transfer learning: communication efficiency, robustness and privacy[J]. IEEE Transactions on Machine Learning in Communications and Networking, 2024, 2: 823-840.
[49] HIDAYAT M A, NAKAMURA Y, DAWTON B, et al. AGC-DP: differential privacy with adaptive Gaussian clipping for federated learning[C]//Proceedings of the 24th IEEE International Conference on Mobile Data Management. Piscataway: IEEE, 2023: 199-208.
[50] ANDREW G, THAKKAR O, MCMAHAN H B, et al. Differentially private learning with adaptive clipping[EB/OL]. [2025-02-18]. https://arxiv.org/abs/1905.03871.
[51] FU J, CHEN Z L, HAN X. Adap DP-FL: differentially private federated learning with adaptive noise[C]//Proceedings of the 2022 IEEE International Conference on Trust, Security and Privacy in Computing and Communications. Piscataway: IEEE, 2022: 656-663.
[52] LI J, PEI J, HUANG H. Communication-efficient robust federated learning with noisy labels[C]//Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York: ACM, 2022: 914-924.
[53] HAN L Q, FAN D, LIU J Y, et al. Federated learning differential privacy preservation method based on differentiated noise addition[C]//Proceedings of the 2023 8th International Conference on Cloud Computing and Big Data Analytics. Piscataway: IEEE, 2023: 285-289.
[54] CAI T T, CHAKRABORTY A, VUURSTEEN L. Optimal federated learning for nonparametric regression with heterogeneous distributed differential privacy constraints[EB/OL]. [2025-02-18]. https://arxiv.org/abs/2406.06755.
[55] SHEN X Y, JIANG H, CHEN Y G, et al. PLDP-FL: federated learning with personalized local differential privacy[J]. Entropy, 2023, 25(3): 485.
[56] LIU W Y, CHENG J H, WANG X L, et al. Hybrid differential privacy based federated learning for Internet of things[J]. Journal of Systems Architecture, 2022, 124: 102418.
[57] LIU Y X, ZHAO S Y, XIONG L, et al. Echo of neighbors: privacy amplification for personalized private federated learning with shuffle model[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2023, 37(10): 11865-11872.
[58] LIU T, HU X Y, XU H R, et al. High-accuracy low-cost privacy-preserving federated learning in IoT systems via adaptive perturbation[J]. Journal of Information Security and Applications, 2022, 70: 103309.
[59] KHALAF O I, ASHOKKUMAR S R, ALGBURI S, et al. Federated learning with hybrid differential privacy for secure and reliable cross-IoT platform knowledge sharing[J]. Security and Privacy, 2024, 7(3): e374.
[60] ZHAO J Z, MAO K M, HUANG C X, et al. Utility optimization of federated learning with differential privacy[J]. Discrete Dynamics in Nature and Society, 2021(1): 3344862.
[61] MA J T, ZHOU Y P, LI Q, et al. The power of bias: optimizing client selection in federated learning with heterogeneous differential privacy[EB/OL]. [2025-02-19]. https://arxiv.org/abs/2408.08642.
[62] 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.
[63] XU Y, XIAO M J, TAN H S, et al. Incentive mechanism for differentially private federated learning in industrial Internet of things[J]. IEEE Transactions on Industrial Informatics, 2022, 18(10): 6927-6939.
[64] 周赞, 张笑燕, 杨树杰, 等. 面向联邦算力网络的隐私计算自适激励机制[J]. 计算机学报, 2023, 46(12): 2705-2725.
ZHOU Z, ZHANG X Y, YANG S J, et al. Adaptive incentive mechanism for privacy computing in federated compute first networks[J]. Chinese Journal of Computers, 2023, 46(12): 2705-2725.
[65] CAI H Y, ZHANG M L, WANG S Y, et al. PLFa-FL: personalized local differential privacy for fair federated learning[C]//Proceedings of the 27th International Conference on Computer Supported Cooperative Work in Design. Piscataway: IEEE, 2024: 2325-2332.
[66] DING J H, LIANG G N, BI J B, et al. Differentially private and communication efficient collaborative learning[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(8): 7219-7227.
[67] ALDAGHRI N, MAHDAVIFAR H, BEIRAMI A. Federated learning with heterogeneous differential privacy[EB/OL]. [2025-02-19]. https://arxiv.org/abs/2110.15252.
[68] XUE R, XUE K P, ZHU B, et al. Differentially private federated learning with an adaptive noise mechanism[J]. IEEE Transactions on Information Forensics and Security, 2024, 19: 74-87.
[69] HU R, GUO Y X, LI H N, et al. Personalized federated learning with differential privacy[J]. IEEE Internet of Things Journal, 2020, 7(10): 9530-9539.
[70] LIAN Z T, WANG W Z, HUANG H K, et al. Layer-based communication-efficient federated learning with privacy pre-servation[J]. IEICE Transactions on Information and Systems, 2022(2): 256-263.
[71] HE Z B, WANG L T, CAI Z P. Clustered federated learning with adaptive local differential privacy on heterogeneous IoT data[J]. IEEE Internet of Things Journal, 2024, 11(1): 137-146.
[72] 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.
[73] ZHU G M, ZHANG J Y, ZHANG S B, et al. Federated learning privacy-preserving method based on Bregman optimization[C]//Proceedings of the 10th IEEE International Conference on Cyber Security and Cloud Computing/2023 IEEE 9th International Conference on Edge Computing and Scalable Cloud. Piscataway: IEEE, 2023: 85-90.
[74] 张少波, 张激勇, 朱更明, 等. 基于Bregman散度和差分隐私的个性化联邦学习方法[J]. 软件学报, 2024, 35(11): 5249-5262.
ZHANG S B, ZHANG J Y, ZHU G M, et al. Personalized federated learning method based on Bregman divergence and differential privacy[J]. Journal of Software, 2024, 35(11): 5249-5262.
[75] WANG Y T, SU Z, PAN Y H, et al. Social-aware clustered federated learning with customized privacy preservation[J]. IEEE/ACM Transactions on Networking, 2024, 32(5): 3654-3668.
[76] HU R, GUO Y X, GONG Y M. Federated learning with sparsified model perturbation: improving accuracy under client-level differential privacy[J]. IEEE Transactions on Mobile Computing, 2024, 23(8): 8242-8255.
[77] SUN X H, YUAN Z S, KONG X G, et al. Communication-efficient and privacy-preserving aggregation in federated learning with adaptability[J]. IEEE Internet of Things Journal, 2024, 11(15): 26430-26443.
[78] ZHANG B T, MAO Y C, HE X M, et al. Balancing privacy and accuracy using significant gradient protection in federated learning[J]. IEEE Transactions on Computers, 2025, 74(1): 278-292.
[79] YANG J W, CHEN S H, WANG G J, et al. GFL-ALDPA: a gradient compression federated learning framework based on adaptive local differential privacy budget allocation[J]. Multimedia Tools and Applications, 2024, 83(9): 26349-26368.
[80] KERKOUCHE R, áCS G, CASTELLUCCIA C, et al. Compression boosts differentially private federated learning[C]//Proceedings of the 2021 IEEE European Symposium on Security and Privacy. Piscataway: IEEE, 2021: 304-318.
[81] CHEN W N, CHOQUETTE-CHOO C A, KAIROUZ P, et al. The fundamental price of secure aggregation in differentially private federated learning[EB/OL]. [2025-02-19]. https://arxiv.org/abs/2203.03761.
[82] LI Z Z, ZHAO H Y, LI B Y, et al. SoteriaFL: a unified framework for private federated learning with communication compression[EB/OL]. [2025-02-19]. https://arxiv.org/abs/2206. 09888.
[83] WEI K, LI J, MA C, et al. Gradient sparsification for efficient wireless federated learning with differential privacy[J]. Science China Information Sciences, 2024, 67(4): 142303.
[84] 李敏, 肖迪, 陈律君. 兼顾通信效率与效用的自适应高斯差分隐私个性化联邦学习[J]. 计算机学报, 2024, 47(4): 924-946.
LI M, XIAO D, CHEN L J. Communication-efficient and utility-aware adaptive Gaussian differential privacy for personalized federated learning[J]. Chinese Journal of Computers, 2024, 47(4): 924-946.
[85] WU X, ZHANG Y T, SHI M Y, et al. An adaptive federated learning scheme with differential privacy preserving[J]. Future Generation Computer Systems, 2022, 127: 362-372.
[86] IQBAL M, TARIQ A, ADNAN M, et al. FL-ODP: an optimized differential privacy enabled privacy preserving federated learning[J]. IEEE Access, 2023, 11: 116674-116683.
[87] CHAMIKARA M A P, LIU D X, CAMTEPE S, et al. Local differential privacy for federated learning[EB/OL]. [2025-02-19]. https://arxiv.org/abs/2202.06053.
[88] BAO E, ZHU Y Z, XIAO X K, et al. Skellam mixture mechanism: a novel approach to federated learning with differential privacy[J]. Proceedings of the VLDB Endowment, 2022, 15(11): 2348-2360.
[89] KODA Y, YAMAMOTO K, NISHIO T, et al. Differentially private aircomp federated learning with power adaptation harnessing receiver noise[C]//Proceedings of the 2020 IEEE Global Communications Conference. Piscataway: IEEE, 2020: 1-6.
[90] LIU R X, CAO Y, YOSHIKAWA M, et al. FedSel: federated SGD under local differential privacy with top-k dimension selection[C]//Proceedings of the 25th International Conference on Database Systems for Advanced Applications. Cham: Springer, 2020: 485-501.
[91] CHENG A D, WANG P S, ZHANG X S, et al. Differentially private federated learning with local regularization and sparsification[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 10112-10121.
[92] 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.
[93] GIRGIS A, DATA D, DIGGAVI S, et al. Shuffled model of differential privacy in federated learning[C]//Proceedings of the 2021 International Conference on Artificial Intelligence and Statistics, 2021: 2521-2529.
[94] KIM M, GüNLü O, SCHAEFER R F. Federated learning with local differential privacy: trade-offs between privacy, utility, and communication[C]//Proceedings of the 2021 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2021: 2650-2654.
[95] 张啸剑, 张雷雷, 张治政. 基于用户级别本地化差分隐私的联邦学习方法[J]. 计算机研究与发展, 2025, 62(2): 472-487.
ZHANG X J, ZHANG L L, ZHANG Z Z. Federated learning method under user-level local differential privacy[J]. Journal of Computer Research and Development, 2025, 62(2): 472-487.
[96] SUN L C, QIAN J W, CHEN X. LDP-FL: practical private aggregation in federated learning with local differential privacy[EB/OL]. [2025-02-20]. https://arxiv.org/abs/2007.15789.
[97] 曹世翔, 陈超梦, 唐朋, 等. 基于函数机制的差分隐私联邦学习算法[J]. 计算机学报, 2023, 46(10): 2178-2195.
CAO S X, CHEN C M, TANG P, et al. Differentially private federated learning with functional mechanism[J]. Chinese Journal of Computers, 2023, 46(10): 2178-2195.
[98] LIU L M, ZHANG J, SONG S H, et al. Binary federated learning with client-level differential privacy[C]//Proceedings of the 2023 IEEE Global Communications Conference. Piscataway: IEEE, 2023: 3849-3854.
[99] SHI Y F, WEI K, SHEN L, et al. Efficient federated learning with enhanced privacy via lottery ticket pruning in edge computing[J]. IEEE Transactions on Mobile Computing, 2024, 23(10): 9946-9958.
[100] WANG B C, CHEN Y G, JIANG H, et al. PPeFL: privacy-preserving edge federated learning with local differential privacy[J]. IEEE Internet of Things Journal, 2023, 10(17): 15488-15500.
[101] ZHANG X, FANG M H, LIU J, et al. Private and communication-efficient edge learning: a sparse differential Gaussian-masking distributed SGD approach[C]//Proceedings of the 21st International Symposium on Theory, Algorithmic Foun-dations, and Protocol Design for Mobile Networks and Mobile Computing. New York: ACM, 2020: 261-270.
[102] CHANDRASEKARAN V, BANERJEE S, PERINO D, et al. Hierarchical federated learning with privacy[C]//Proceedings of the 2024 IEEE International Conference on Big Data. Piscataway: IEEE, 2024: 1516-1525.
[103] ZHANG M F, XIE Z H, YIN L H. Private and communication-efficient federated learning based on differentially private sketches[EB/OL]. [2025-02-20]. https://arxiv.org/abs/2410.05733.
[104] CHEN C L, LIAN Z T, SU C H, et al. Evaluating differential privacy in federated continual learning: a catastrophic forgetting-performance tradeoff analysis[C]//Proceedings of the 12th International Symposium on Computing and Networking. Piscataway: IEEE, 2024: 135-141.
[105] JIANG Y, TONG X D, LIU Z Y, et al. Efficient federated unlearning with adaptive differential privacy preservation[C]//Proceedings of the 2024 IEEE International Conference on Big Data. Piscataway: IEEE, 2024: 7822-7831.