Terminal data privacy-preserving scheme based on hierarchical federated learning

doi:10.11772/j.issn.1001-9081.2025040437

Journal of Computer Applications ›› 2026, Vol. 46 ›› Issue (3): 830-838.DOI: 10.11772/j.issn.1001-9081.2025040437

• Cyber security • Previous Articles Next Articles

Terminal data privacy-preserving scheme based on hierarchical federated learning

Huan PING, Zhanguo XIA(), Sicheng LIU, Qihan LIU, Chunlei LI

School of Computer Science and Technology，China University of Mining and Technology，Xuzhou Jiangsu 221116，China

Received:2025-04-25 Revised:2025-06-26 Accepted:2025-06-30 Online:2025-07-03 Published:2026-03-10
Contact: Zhanguo XIA
About author:PING Huan， born in 1999， M. S. candidate. Her research interests include machine learning， federated learning， privacy protection.
LIU Sicheng， born in 2001， M. S. candidate. His research interests include hyperspectral image， LiDAR， machine learning， data mining， multimodal classification.
LIU Qihan， born in 2001， M. S. candidate. His research interests include deep learning， computer vision， pedestrian trajectory prediction.
LI Chunlei， born in 2001， M. S. candidate. His research interests include machine learning， deep learning， time series prediction.
Supported by:
National Natural Science Foundation of China(62272461)

基于多层联邦学习的终端数据隐私保护方案

平欢, 夏战国(), 刘思诚, 刘奇翰, 李春磊

中国矿业大学计算机科学与技术学院，江苏徐州 221116

通讯作者: 夏战国
作者简介:平欢（1999—），女，河北沧州人，硕士研究生，主要研究方向：机器学习、联邦学习、隐私保护
刘思诚（2001—），男，江苏徐州人，硕士研究生，主要研究方向：高光谱图像、激光雷达、机器学习、数据挖掘、多模态分类
刘奇翰（2001—），男，江苏徐州人，硕士研究生，主要研究方向：深度学习、计算机视觉、行人轨迹预测
李春磊（2001—），男，山东济南人，硕士研究生，主要研究方向：机器学习、深度学习、时间序列预测。
基金资助:
国家自然科学基金资助项目(62272461)

Abstract

Abstract:

Federated learning， as a distributed machine learning framework for data privacy protection， faces several challenges such as that the traditional cloud-edge-device structure cannot meet the increasingly strict data security regulations and the exponential growth of data. At the same time， the lightweight trend of edge devices leads to limited computing capabilities. To address these issues， an Optional Hierarchical Federated Learning （OHFL） scheme facing multi-level supervision and heterogeneous resource environments was proposed. Firstly， a tree-structured multi-layer architecture was adopted to configure the number of edge layers and the number of servers per layer flexibly， so as to adapt to supervision levels and resource distribution in different scenarios. Secondly， a differential privacy mechanism was introduced on the basis of ensuring communication efficiency， homomorphic encryption was applied to certain neural network layers， and the encryption tasks were offloaded to the nearest edge servers to distribute the computational burden. Experimental results show that the OHFL scheme achieves a classification accuracy of 97.82% on the MNIST Independent Identically Distributed （IID） dataset， with the additional encryption mechanism using Convolutional Neural Network （CNN） and ResNet18 incurring only a time overhead of 6.24 s and 6.80 s per round， verifying that the OHFL scheme improves the system efficiency of computation and communication significantly. It can be seen that the proposed scheme improves the security and adaptability of hierarchical federated learning architecture theoretically， and provides a feasible solution for meeting multi-level supervision and efficient secure computation in practical applications， especially suitable for scenarios such as Internet of Things （IoT） and healthcare with data sensitivity and resource heterogeneity.

Key words: federated learning, hierarchical architecture, differential privacy, homomorphic encryption, privacy protection

摘要：

作为一种保护数据隐私的分布式机器学习框架，联邦学习面临着传统云-边-端三层结构难以满足日益严格的数据安全法规和指数级增长数据的挑战，同时边缘设备轻量化趋势导致计算能力受限。为解决上述问题，提出一种面向多级监管和异构资源环境的可选多层联邦学习（OHFL）方案。首先，采用树形多层结构实现边缘层数与每层服务器数量的灵活配置，从而适配不同应用场景下的监管层级和资源分布；其次，在保证通信效率的基础上，引入差分隐私机制，同时对部分神经网络层采用同态加密，并将加密任务下沉至最邻近的边缘服务器以分散计算压力。实验结果表明，OHFL方案在MNIST独立同分布（IID）数据集上达到了97.82%的分类准确率，且新增加密机制分别使用卷积神经网络（CNN）和ResNet18带来的时间损失仅为每轮6.24 s和6.80 s，说明OHFL方案显著提升了系统的计算与通信效率。可见，所提方案不仅在理论上提升了多层级联邦学习架构下的安全性与适应性，而且为实际应用中满足多级监管和高效安全计算需求提供了可行路径，特别适用于数据敏感且资源异构的物联网（IoT）与医疗等场景。

关键词: 联邦学习, 分层架构, 差分隐私, 同态加密, 隐私保护

CLC Number:

TP309.2

Huan PING, Zhanguo XIA, Sicheng LIU, Qihan LIU, Chunlei LI. Terminal data privacy-preserving scheme based on hierarchical federated learning[J]. Journal of Computer Applications, 2026, 46(3): 830-838.

平欢, 夏战国, 刘思诚, 刘奇翰, 李春磊. 基于多层联邦学习的终端数据隐私保护方案[J]. 《计算机应用》唯一官方网站, 2026, 46(3): 830-838.

Figures/Tables 10

Fig. 1 System architecture of OHFL

Fig. 2 System flow

Tab. 1 Impact of different numbers of edge layers and edge servers on model accuracy

层数	不同边缘服务器数下的模型准确率/%
层数	［4］	［4，2］	［4，3，2］	［6，4］	［6，4，3，2］	［8，4］
1	97.02	—	—	—	—	—
2	—	96.90	—	96.23	—	95.93
3	—	—	96.83	—	—	—
4	—	—	—	—	96.08	—

Fig. 3 Model accuracies on MNIST dataset with different numbers of clients and participation rates

Fig. 4 Model accuracies on MNIST dataset under different privacy protection conditions

Fig. 5 Model accuracies on CIFAR-10 dataset under different privacy protection conditions

Fig. 6 Model accuracies on MNIST dataset under different privacy budgets

Tab. 2 Impact of different privacy protection measures on training time

神经网络	方法	每轮耗时/s	因新保护措施增加的时间/s
CNN	方法1	8.40	—
	方法2	9.11	0.71
	方法3	15.35	6.24
	方法4	117.67	109.27
ResNet18	方法1	122.50	—
	方法2	151.25	28.57
	方法3	158.05	6.80
	方法4	3 421.05	3 298.55

Fig. 7 Model accuracies on non-IID data of MNIST dataset under different levels of privacy protection

Fig. 8 Changes of a certain image before and after leakage in CIFAR-10 dataset

References 38

[1]	Analytics IoT. State of IoT summer 2024 ［EB/OL］. ［2024-11-15］..
[2]	MA C， LI J， DING M， et al. On safeguarding privacy and security in the framework of federated learning ［J］. IEEE Network， 2020， 34（4）： 242-248.
[3]	WAINAKH A， GUINEA A S， GRUBE T， et al. Enhancing privacy via hierarchical federated learning ［C］// Proceedings of the 2020 IEEE European Symposium on Security and Privacy Workshops. Piscataway： IEEE， 2020： 344-347.
[4]	BONAWITZ K， IVANOV V， KREUTER B， et al. Practical secure aggregation for privacy-preserving machine learning ［C］// Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security. New York： ACM， 2017： 1175-1191.
[5]	DWORK C. Differential privacy ［C］// Proceedings of the 2006 International Colloquium on Automata， Languages， and Programming， LNCS 4052. Berlin： Springer， 2006： 1-12.
[6]	ACAR A， AKSU H， ULUAGAC A S， et al. A survey on homomorphic encryption schemes： theory and implementation ［J］. ACM Computing Surveys， 2018， 51（4）： No.79.
[7]	YANG Z， HU S， CHEN K. FPGA-based hardware accelerator of homomorphic encryption for efficient federated learning ［EB/OL］. ［2024-11-23］..
[8]	SÉBERT A G， CHECRI M， STAN O， et al. Combining homomorphic encryption and differential privacy in federated learning ［C］// Proceedings of the 20th Annual International Conference on Privacy， Security and Trust. Piscataway： IEEE， 2023： 1-7.
[9]	ZHANG J， FAY D， JOHANSSON M. Dynamic privacy allocation for locally differentially private federated learning with composite objectives ［C］// Proceedings of the 2024 IEEE International Conference on Acoustics， Speech and Signal Processing. Piscataway： IEEE， 2024： 9461-9465.
[10]	HAN Q， LU S， WANG W， et al. Privacy preserving and secure robust federated learning： a survey ［J］. Concurrency and Computation： Practice and Experience， 2024， 36（13）： No.e8084.
[11]	MALIK P， ALIRAJPURWALA T， KAUSHAL S， et al. Scalability and robustness of federated learning systems： challenges and solutions ［J］. International Journal of Scientific Research in Engineering and Management， 2024， 8（6）： 1-10.
[12]	COLLINS E， WANG M. Federated learning： a survey on privacy-preserving collaborative intelligence ［EB/OL］. ［2025-06-14］..
[13]	PAILLIER P. Public-key cryptosystems based on composite degree residuosity classes ［C］// Proceedings of the 1999 International Conference on the Theory and Applications of Cryptographic Techniques， LNCS 1592. Berlin： Springer， 1999： 223-238.
[14]	LeCUN Y， BOTTOU L， BENGIO Y， et al. Gradient-based learning applied to document recognition ［J］. Proceedings of the IEEE， 1998， 86（11）： 2278-2324.
[15]	KRIZHEVSKY A. Learning multiple layers of features from tiny images ［R/OL］. ［2024-04-25］..
[16]	ZHU L， LIU Z， HAN S. Deep leakage from gradients ［C］// Proceedings of the 33rd International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2019： 14774-14784.
[17]	GEIPING J， BAUERMEISTER H， DRÖGE H， et al. Inverting gradients — how easy is it to break privacy in federated learning？［C］// Proceedings of the 34th International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2020： 16937-16947.
[18]	WAINAKH A， VENTOLA F， MÜßIG T， et al. User-level label leakage from gradients in federated learning ［EB/OL］. ［2024-11-14］..
[19]	YIN H， MALLYA A， VAHDAT A， et al. See through gradients： image batch recovery via GradInversion ［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 16332-16341.
[20]	YUE K， JIN R， WONG C W， et al. Gradient obfuscation gives a false sense of security in federated learning ［C］// Proceedings of the 32nd USENIX Security Symposium. Berkeley： USENIX Association， 2023： 6381-6398.
[21]	VOGELS T， KARIMIREDDY S P， JAGGI M. PowerSGD： practical low-rank gradient compression for distributed optimization［C］// Proceedings of the 33rd International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2019： 14269-14278.
[22]	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， 2016： 308-318.
[23]	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.
[24]	SHI L， SHU J， ZHANG W， et al. HFL-DP： hierarchical federated learning with differential privacy ［C］// Proceedings of the 2021 IEEE Global Communications Conference. Piscataway： IEEE， 2021： 1-7.
[25]	WU X， ZHANG Y， SHI M， et al. An adaptive federated learning scheme with differential privacy preserving ［J］. Future Generation Computer Systems， 2022， 127： 362-372.
[26]	WANG B， CHEN Y， 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.
[27]	SHI Y， LIU Y， WEI K， et al. Make landscape flatter in differentially private federated learning ［C］// Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2023： 24552-24562.
[28]	McMAHAN H B， RAMAGE D， TALWAR K， et al. Learning differentially private recurrent language models ［EB/OL］. ［2024-11-16］..
[29]	ZHOU T. Hierarchical federated learning with Gaussian differential privacy ［C］// Proceedings of the 4th International Conference on Advanced Information Science and System. New York： ACM， 2022： No.61.
[30]	LONG Y， ZHANG J， WANG G， et al. Hierarchical federated learning with global differential privacy ［J］. Electronic Research Archive， 2023， 31（7）： 3741-3758.
[31]	LI S， LIU Y， FENG F， et al. HierFedPDP： hierarchical federated learning with personalized differential privacy ［J］. Journal of Information Security and Applications， 2024， 86： No.103890.
[32]	JIANG S， WANG X， QUE Y， et al. Fed-MPS： federated learning with local differential privacy using model parameter selection for resource-constrained CPS ［J］. Journal of Systems Architecture， 2024， 150： No.103108.
[33]	RIVEST R L， SHAMIR A， ADLEMAN L. A method for obtaining digital signatures and public-key cryptosystems ［J］. Communications of the ACM， 1983， 26（1）： 96-99.
[34]	王腾，霍峥，黄亚鑫，等. 联邦学习中的隐私保护技术研究综述［J］. 计算机应用， 2023， 43（2）： 437-449.
	WANG T， HUO Z， HUANG Y X， et al. Review on privacy protection technologies in federated learning ［J］. Journal of Computer Applications， 2023， 43（2）： 437-449.
[35]	北京理工大学. 基于差分隐私和同态加密的联邦学习隐私保护方法： 202311049045.3［P］. 2024-01-19.
	Beijing Institute of Technology. Federated learning privacy protection method based on differential privacy and homomorphic encryption： 202311049045.3 ［P］. 2024-01-19.
[36]	张海超，赖金山，刘东，等. 边缘计算下的轻量级联邦学习隐私保护方案［J］. 计算机技术与发展， 2023， 33（9）： 161-167.
	ZHANG H C， LAI J S， LIU D， et al. Lightweight federated learning privacy protection scheme under edge computing ［J］. Computer Technology and Development， 2023， 33（9）： 161-167.
[37]	McMAHAN H B， MOORE E， RAMAGE D， et al. Communication-efficient learning of deep networks from decentralized data ［C］// Proceedings of the 20th International Conference on Artificial Intelligence and Statistics. New York： JMLR.org， 2017： 1273-1282.
[38]	LIU L， ZHANG J， SONG S H， et al. Client-edge-cloud hierarchical federated learning ［C］// Proceedings of the 2020 IEEE International Conference on Communications. Piscataway： IEEE， 2020： 1-6.

Terminal data privacy-preserving scheme based on hierarchical federated learning

基于多层联邦学习的终端数据隐私保护方案

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 10

References 38

Related Articles 15

Recommended Articles

Metrics

[1]	Enkang XI, Jing FAN, Yadong JIN, Hua DONG, Hao YU, Yihang SUN. Review of threats faced by federated learning in privacy and security field [J]. Journal of Computer Applications, 2026, 46(3): 798-808.
[2]	Lili HE, Xinru GUAN, Lei ZHANG, Sheng JIANG, Chengjie JIANG. Panorama and future of location privacy protection in internet of vehicles [J]. Journal of Computer Applications, 2026, 46(3): 809-820.
[3]	Qi ZHONG, Shufen ZHANG, Zhenbo ZHANG, Yinlong JIAN, Zhongrui JING. Detection and defense mechanism for poisoning attacks to federated learning [J]. Journal of Computer Applications, 2026, 46(2): 445-457.
[4]	Kejia ZHANG, Zhijun FANG, Nanrun ZHOU, Zhicai SHI. Personalized federated learning method based on model pre-assignment and self-distillation [J]. Journal of Computer Applications, 2026, 46(1): 10-20.
[5]	Yinlong JIAN, Xuebin CHEN, Zhongrui JING, Qi ZHONG, Zhenbo ZHANG. Data augmentation scheme based on conditional generative adversarial network in federated learning [J]. Journal of Computer Applications, 2026, 46(1): 21-32.
[6]	Na FAN, Chuang LUO, Zehui ZHANG, Mengyao ZHANG, Ding MU. Semantic privacy protection mechanism of vehicle trajectory based on improved generative adversarial network [J]. Journal of Computer Applications, 2026, 46(1): 169-180.
[7]	Hao YU, Jing FAN, Yihang SUN, Yadong JIN, Enkang XI, Hua DONG. Federated split learning optimization method under edge heterogeneity [J]. Journal of Computer Applications, 2026, 46(1): 33-42.
[8]	Sheping ZHAI, Pengju ZHU, Rui YANG, Jiayiteng LIU. Blockchain-based identity management system for internet of things [J]. Journal of Computer Applications, 2025, 45(9): 2873-2881.
[9]	Bohan ZHANG, Le LYU, Junchang JING, Dong LIU. Genetic algorithm-based community hiding method in attribute networks [J]. Journal of Computer Applications, 2025, 45(9): 2817-2826.
[10]	Hao YU, Jing FAN, Yihang SUN, Hua DONG, Enkang XI. Survey of statistical heterogeneity in federated learning [J]. Journal of Computer Applications, 2025, 45(9): 2737-2746.
[11]	Yan YAN, Feifei LI, Yaqin LYU, Tao FENG. Secure and efficient frequency estimation method based on shuffled differential privacy [J]. Journal of Computer Applications, 2025, 45(8): 2600-2611.
[12]	Jintao SU, Lina GE, Liguang XIAO, Jing ZOU, Zhe WANG. Detection and defense scheme for backdoor attacks in federated learning [J]. Journal of Computer Applications, 2025, 45(8): 2399-2408.
[13]	Lina GE, Mingyu WANG, Lei TIAN. Review of research on efficiency of federated learning [J]. Journal of Computer Applications, 2025, 45(8): 2387-2398.
[14]	Hongyang ZHANG, Shufen ZHANG, Zheng GU. Federated learning algorithm for personalization and fairness [J]. Journal of Computer Applications, 2025, 45(7): 2123-2131.
[15]	Li’e WANG, Caiyi LIN, Yongdong LI, Xingcheng FU, Xianxian LI. Digital content copyright protection and fair tracking scheme based on blockchain [J]. Journal of Computer Applications, 2025, 45(6): 1756-1765.