The DOI matches its Crossref record; 47 of the 48 references it cites were found in a registry or an index.
Clustered Federated Learning With Adaptive Local Differential Privacy on Heterogeneous IoT Data
Abstract
The Internet of Things (IoT) is penetrating many aspects of our daily life with the proliferation of artificial intelligence applications. Federated learning (FL) has emerged as a promising paradigm enabling many intelligent IoT applications; however, the transmitted model gradients or weights still encode private information, which can be exploited to launch inference attacks. One popular way is to apply local differential privacy (LDP) into FL. However, existing work does not provide a practical solution due to two issues. First, the fine-grained range difference of weights in different layers of an FL model has not been explicitly considered. Second, the accumulated privacy budget may cause a budget explosion. In this article, we propose a local differentially private scheme to train clustered FL models on heterogeneous IoT data by using adaptive clipping, weight compression, and parameter shuffling (namely, ACS-FL), aimed at mitigating the curse of dimensionality, the amount of LDP noise, and the communication overhead of IoT devices. Empirical evaluations on MNIST, fashion-MNIST, and Federated Extended MNIST demonstrate that ACS-FL achieves a superior performance in balancing the tradeoff between privacy and utility.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Through adding noise to updates, differential privacy confirms that personal data cannot be derived from the final aggregated model, an important feature for handling sensitive health data in FL applications [87].”
From Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration (2024) · cites this paper as [87]
In the citing paper
“Distinctive privacy is broadly adopted in FL to protect private contributions to model updates.”
From Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration (2024) · cites this paper as [87]
Citations
Cites
Communication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215
Deep Learning with Differential Privacy
Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016) · Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2976749.2978318 · Cited by 6,578
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Xiao, H., Rasul, K., & Vollgraf, R. (2017) · arXiv · doi:10.48550/arxiv.1708.07747 · Cited by 6,108
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2014) · Foundations and Trends® in Theoretical Computer Science · doi:10.1561/0400000042 · Cited by 5,557
Federated Optimization in Heterogeneous Networks
Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2018) · arXiv · doi:10.48550/arxiv.1812.06127 · Cited by 4,023
Lin, J., Yu, W., Zhang, N., Yang, X., Zhang, H., & Zhao, W. (2017) · IEEE Internet of Things Journal · doi:10.1109/jiot.2017.2683200 · Cited by 2,793
Federated Learning with Non-IID Data
Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., & Chandra, V. (2018) · arXiv · doi:10.48550/arxiv.1806.00582 · Cited by 2,077
SecureML: A System for Scalable Privacy-Preserving Machine Learning
Mohassel, P., & Zhang, Y. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.12 · Cited by 1,936
Zhu, L., & Han, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-63076-8_2 · Cited by 1,906
Towards Personalized Federated Learning
Tan, A. Z., Yu, H., Cui, L., & Yang, Q. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3160699 · Cited by 1,474
Research works printed but not linked: 2
- Xu, 2021, FedMood: Federated learning on mobile health data for mood detection, arXiv:2102.09342 · arXiv
- LeCun, 2010, MNIST Handwritten Digit Database
Cited by
Sorted by citations
Abbas, S. R., Abbas, Z., Zahir, A., & Lee, S. W. (2024) · Healthcare · doi:10.3390/healthcare12242587 · Cited by 228
Privacy-Preserving Federated Learning for Intrusion Detection in IoT Environments: A Survey
Vyas, A., Lin, P., Hwang, R., & Tripathi, M. (2024) · IEEE Access · doi:10.1109/access.2024.3454211 · Cited by 115
“The empirical evaluations in [179] demonstrate that the proposed ACS-FL (adaptive clipping, weight compression, and parameter shuffling) scheme achieves superior performance in striking an equilibrium between privacy preservation and utility maximization.”
BackgroundInfluentialMohammadi, S., Balador, A., Sinaei, S., & Flammini, F. (2024) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2024.104918 · Cited by 93
IOFL: Intelligent-Optimization-Based Federated Learning for Non-IID Data
Li, X., Zhao, H., & Deng, W. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3354942 · Cited by 60
“Regarding privacy protection issues in FL, some existing researches typically combine FL with cryptographic techniques of differential privacy, multiparty secure computing, and homomorphic encryption, or replace client server communication content [30], [31], [32].”
BackgroundDigital Twin-Assisted Federated Learning Service Provisioning Over Mobile Edge Networks
Zhang, R., Xie, Z., Yu, D., Liang, W., & Cheng, X. (2023) · IEEE Transactions on Computers · doi:10.1109/tc.2023.3337317 · Cited by 36
“There are many investigations on implementing FL in MEC networks [24], [25], [26], [27].”
BackgroundCheng, Y., Zhang, W., Zhang, Z., Kang, J., Xu, Q. M., Wang, S., & Niyato, D. T. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3529487 · Cited by 43
“We consider that there exists an optimal solution w ∗ i for cluster To begin with, we apply the following commonly used assumptions by many relevant works [13], [31], [32]: Assumption 2: For ∀ x, y , the loss function where L > 0 .”
Wang, D., & Guan, S. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102796 · Cited by 33
Privacy-Preserving Federated Learning-Based Intrusion Detection System for IoHT Devices
Mosaiyebzadeh, F., Pouriyeh, S., Han, M., Liu, L., Xie, Y., Zhao, L., & Batista, D. M. (2024) · Electronics · doi:10.3390/electronics14010067 · Cited by 27
A Survey of Differential Privacy Techniques for Federated Learning
Wang, X., Jiaqian, L., Xueshuang, D., Zhang, H., & Lianshan, S. (2024) · IEEE Access · doi:10.1109/access.2024.3523909 · Cited by 28
An adaptive asynchronous federated learning framework for heterogeneous Internet of things
Zhang, W., Deng, D., Wu, X., Zhao, W. G., Liu, Z., Zhang, T., Kang, J., & Niyato, D. T. (2024) · Information Sciences · doi:10.1016/j.ins.2024.121458 · Cited by 20
A robust and personalized privacy-preserving approach for adaptive clustered federated distillation
Shawkat, M., Ali, Z. H., Salem, M. M., & El-desoky, A. (2025) · Scientific Reports · doi:10.1038/s41598-025-96468-8 · Cited by 20
“However, the model gradients or weights may still contain private information, which poses a risk of inference attacks 58 .”
Privacy-Preserving Serverless Federated Learning Scheme for Internet of Things
Wu, C., Zhang, L., Xu, L., Choo, K. R., & Zhong, L. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3380597 · Cited by 20
“…in a centralized manner (i.e., utilizing a central server) and that such schemes commonly integrate differential privacy (DP) [6], [7], [8], [9], [10] and secure multiparty computation (MPC) [11], [12], [13], [14], [15], [16], [17], [18], [19], [20], [21], [22], [23] to support data privacy.”
BackgroundAdaptive Federated Learning via New Entropy Approach
Zheng, S., Yuan, W., Wang, X., & Duan, L. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3402080 · Cited by 22
Manzoor, H. U., Jafri, A. R., & Zoha, A. (2024) · Internet of Things · doi:10.1016/j.iot.2024.101376 · Cited by 28
Data distribution inference attack in federated learning via reinforcement learning support
Yu, D., Zhang, H., Huang, Y., & Xie, Z. (2024) · High-Confidence Computing · doi:10.1016/j.hcc.2024.100235 · Cited by 18
RAFLS: RDP-Based Adaptive Federated Learning With Shuffle Model
Wang, S., Gai, K., Yu, J., Zhu, L., Wu, H., Wei, C., Yan, Y., Zhang, H., & Choo, K. R. (2024) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2024.3429503 · Cited by 18
“On the other hand, some other work [7], [15], [16] have explored the Bernoulli distribution for partitioning perturbation parameters of different layer weights, based on a smaller variance among the estimated model weights of each layer.”
Cao, Y., Ma, J., He, Z., & Li, Y. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3528624 · Cited by 17
“Exemplary CFL approaches include [14], [15], [19], [20], [21], [22], [23], [24], [25], [26], [27], [28], and [29].”
Towards Privacy-Enhanced and Robust Clustered Federated Learning
Xu, Y., Tan, Y., Zhang, C., Sun, P., Zhang, Y., Ren, J., Jiang, H., & Zhang, Y. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3547149 · Cited by 16
He, Z., Li, Y., Seo, D., & Cai, Z. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102481 · Cited by 15
ElZemity, A., & Arief, B. (2024) · IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) · doi:10.1109/ithings-greencom-cpscom-smartdata-cybermatics62450.2024.00072 · Cited by 16
“He et al. [51] introduce adaptive local differential privacy mechanisms in FL for heterogeneous IoT data, focusing on balancing the trade-off between privacy and utility.”
BackgroundA Survey of Federated Learning for mmWave Massive MIMO
Nugroho, V. A., & Lee, B. M. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3397302 · Cited by 16
Aldp-fl: an adaptive local differential privacy-based federated learning mechanism for IoT
Li, J., Lu, M., Zhang, J., & Wu, J. (2024) · International Journal of Information Security · doi:10.1007/s10207-024-00933-w · Cited by 14
“The proliferation of IoT devices and exponential data growth has driven the development of differential privacy-based federated learning in the IoT domain [20].”
Application of Federated Learning in Cardiology: Key Challenges and Potential Solutions
Rahman, S., Karmarkar, C., & Islam, S. M. S. (2024) · Mayo Clinic Proceedings Digital Health · doi:10.1016/j.mcpdig.2024.09.005 · Cited by 12
“…threats is differential privacy, which introduces noise to the model parameters and makes at-tackers unable to retrieve the actual model speci fi cs. 14 Unfortunately, this solution compromises the model ’ s performance as the added noise affects the accuracy and reliability of the model ’ s…”
Federated Learning for Heterogeneous Data Integration and Privacy Protection
Gong, C., Zhang, X., Lin, Y., Su, P.-C., Lü, H., & Zhang, J. (2025) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd64889.2025.11033572 · Cited by 16
Blockchain-based privacy-preserving multi-tasks federated learning framework
Jia, Y., Xiong, L., Fan, Y., Liang, W., Xiong, N. N., & Xiao, F. (2024) · Connection Science · doi:10.1080/09540091.2023.2299103 · Cited by 12
Li, Y., Du, W., Han, L., Zhang, Z., & Liu, T. (2023) · Sensors · doi:10.3390/s23239305 · Cited by 11
“He et al. [25] proposed an LDP method that takes into account the budget explosion problem that may occur when adding differential privacy.”
MethodDeep reinforcement learning based resource provisioning for federated edge learning
Chen, X., Pang, J., & Sun, T. (2024) · High-Confidence Computing · doi:10.1016/j.hcc.2024.100264 · Cited by 11
Federated Learning for Smart Cities: A Thematic Review of Challenges and Approaches
Alterkawi, L., & Dib, F. K. (2025) · Future Internet · doi:10.3390/fi17120545 · Cited by 16
“He et al. [52] proposed a federated clustered learning framework that integrates adaptive local differential privacy (LDP) for heterogeneous IoT data.”
Privacy-Preserving Computing in the Healthcare Using Federated Learning
Khan, S. (2024) · Advances in marketing, customer relationship management, and e-services book series · doi:10.4018/979-8-3693-2165-2.ch015 · Cited by 10
He, Y., Li, P., Ni, J., Deng, X., Lu, H., Zhang, J., & Yang, L. T. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3341637 · Cited by 11
“DP-based solutions should carefully design the DP noises added to local models, otherwise they negatively affect the convergence of the global model and generally require more training time to achieve the desired accuracy [10], [29].”
BackgroundXia, Y., Liu, Y., Chen, J., Liang, Y., Khan, F., Alturki, R., & Wang, X. (2024) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2024.3517739 · Cited by 9
“He et al. [22] introduced ACS-FL, which uses adaptive clipping, weight compression, and Authorized licensed use limited to the terms of the applicable license agreement with IEEE.”
Utility-Enhanced Personalized Privacy Preservation in Hierarchical Federated Learning
Chen, J., Jiang, H., & Hu, Q. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3531919 · Cited by 9
“The inclusion of the shuffler in our mechanism is grounded in common practices in privacy-preserving mechanisms [31], [43], [44].”
Li, Y., Qin, X., Geng, J., Chen, R., Hou, Y., Gong, Y., Pan, M., & Zhang, P. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3365477 · Cited by 9
“Following FL principle of training deep neural networks (DNNs) locally without exposing raw data [4], FL over mobile devices fosters numerous promising applications in various domains.”
BackgroundOptimizing Federated Learning: Addressing Key Challenges in Real-World Applications
Kang, N., Lim, Y., & Im, J. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3558910 · Cited by 8
“For example, Adaptive Local DP (ALDP) [146] modifies the noise added to each model weight according to its sensitivity, improving the balance between privacy and performance.”
Federated Graph Learning via Constructing and Sharing Feature Spaces for Cross-Domain IoT
Chen, J., Zhuo, S., He, J., Qiu, W., Zhang, Q., Xiong, Z., Zheng, Z., Tang, Y., Chen, M., Wang, C., et al. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3560635 · Cited by 8
“Moreover, existing FGL [11], [12], [13], [14], [15] potentially assumes that distributed data is preprocessed using certain methods to ensure that all data reside in a consistent feature space.”
Han, J., Wang, L., Liu, Z., Qin, B., Zhang, K., & Li, W. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3595533 · Cited by 8
“On the other hand, LDP has gradually been introduced into FL frameworks, where gradients uploaded by clients are perturbed to protect privacy against untrusted servers [25], [26].”
Zhang, W., Zhan, D., Yu, H., Zhang, L., Zhao, B., Du, X., & Tian, Z. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103657 · Cited by 12
A Lightweight and Accuracy-Lossless Privacy-Preserving Method in Federated Learning
Liu, Z., Yang, C., Ding, Y., Liang, H., & Wang, Y. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3478208 · Cited by 8
“He et al. [19] constructed a local differential private scheme that can train cluster federation on heterogeneous IoT data by using techniques, such as adaptive clipping, weight compression, and parameter transformation to learn the model and mitigate the dimensionality, LDP noise amount, and…”
Privacy-Preserving Multimodal Sentiment Analysis
Xu, H., Li, W., Takabi, D., Seo, D., & Cai, Z. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3527864 · Cited by 7
“2) Differential privacy-based approaches are proposed to provide a theoretical guarantee of data privacy protection by adding Laplace noise based on differential privacy mechanisms [22], [58], [59], [60], [61], [62].”
Enhancing Privacy-Preserving Knowledge Graph Embeddings with Federated Learning for IoT Services
Sun, H., Bi, X., Tu, Z., Zhao, B., Zhang, K., Chu, D., & Xu, X. (2025) · ACM Transactions on Internet Technology · doi:10.1145/3747351 · Cited by 9
“ACS-FL [18] proposes a local differential privacy ( LDP ) scheme to train clustered FL models on heterogeneous IoT data, aimed at mitigating the curse of dimensionality, the amount of LDP noise, and the communication overhead of IoT devices.”
He, Z.-B., Zhang, F.-P., Li, Y., Cao, Y.-L., & Cai, Z.-P. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3391342 · Cited by 9
“pFL has emerged as a solution to FL’s data heterogeneity problem, allowing clients to train models tailored to their specific data distributions and addressing non-iid data challenges [29], [30], [31].”
BackgroundSecure Federated Learning for Multi-Party Network Monitoring
Lytvyn, O., & Nguyen, G. (2024) · IEEE Access · doi:10.1109/access.2024.3486810 · Cited by 10
Federated Learning on Heterogeneous Images in Internet of Biomedical Things
Li, Y., He, Z., He, P., & Cao, Y. (2024) · Big Data Mining and Analytics · doi:10.26599/bdma.2024.9020067 · Cited by 7
Wang, D., Gao, Y., Pang, S., Zhang, C., Zhang, X., & Li, M. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3536035 · Cited by 6
“CAFL [22] fine-tunes noise application at a more fine-grained parameter level, offering novel perturbation techniques, and ACS-FL [23] refines this by randomizing parameter values within spe-cific ranges, balancing noise application and accuracy.”
Secure Federated Learning on the Basis of Adaptive Local Differential Privacy
Shen, X., Guo, J., Wang, B., & Liu, S. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3625938 · Cited by 6
“In contrast, if the value of the privacy budget is too large, the small amounts of perturbation introduced into the model weights will not be su ffi cient for ensuring the privacy of the weights [12].”
InfluentialADPFL: Adaptive Differential Privacy-Enhanced Federated Learning
Xu, X., Li, Y., Lu, L., & Tianyin, W. A. N. G. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3611410 · Cited by 8
“Local di ff erential privacy (LDP) [9], [10], [11], [12] o ff ers a promising alternative by adding noise to model parameters, preserving statistical properties while preventing the exposure of original parameters.”
CHPFL: Clustered adaptive hierarchical federated learning for edge-level personalization
Song, L., Li, J., Jiang, H., Wei, S., & Guo, Y. (2025) · High-Confidence Computing · doi:10.1016/j.hcc.2025.100343 · Cited by 7
Adaptive Edge-Level Personalization on Hierarchical Federated Learning
Song, L., Li, J., Jiang, H., Wei, S., & Guo, Y. (2023) · IEEE International Performance, Computing, and Communications Conference · doi:10.1109/ipccc59175.2023.10253826 · Cited by 6
A Robust Coverless Audio Steganography Based on Differential Privacy Clustering
Feng, Y., Xu, L., Lu, X., Zhang, G., & Rao, W. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3543107 · Cited by 6
“He et al. [34] incorporated differential privacy clustering in federated learning to aggregate heterogeneous models while preserving privacy.”
StarCPFL: Star-Centric Personalized Federated Learning with layer-wised clustering
Rui, X., Liang, W., Chen, Y., He, D., Jin, K., Li, K., & Tsang, K. F. (2025) · Future Generation Computer Systems · doi:10.1016/j.future.2025.108037 · Cited by 5
Sun, B., Song, X., & Tu, Y. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3598149 · Cited by 5
“It clusters clients with similar data distributions and trains a shared model within each cluster, allowing for more targeted learning while still retaining common knowledge across clients [39], [40].”
Khan, M. A., Rais, R. N. B., Khalid, O., & Deriche, M. A. (2025) · IEEE Access · doi:10.1109/access.2025.3608856 · Cited by 5
“In CL, the aggregation of diverse data into a unified global dataset often leads to overfitting on dominant classes, resulting in suboptimal generalization for underrepresented classes or clients [10].”
A Secure and Lightweight Aggregation Method for Blockchain-based Distributed Federated Learning
Huang, H., Duan, L., Li, C., & Ni, W. (2024) · IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws62655.2024.00066 · Cited by 5
“To address the issue of data privacy leakage due to inference attacks on model parameters, the current predominant preventive methods encompass homomorphic encryption (HE) [12], [13], differential privacy (DP) [14], [15], and secure multiparty computation (SMPC) [16], [17].”
BackgroundMethodHeterogeneity-aware device selection for clustered federated learning in IoT
Zhang, H., Li, Z., Xi, S., Zhao, X., Liu, J., & Zhang, P. (2024) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-024-01869-7 · Cited by 7
DPFedSAM-Meas: Comparison Of Differential Privacy Federated Learning In Medical Image Classification
Jiang, S., Wang, Z., He, Z., Li, Y., Li, X., Chi, H., & Du, X. (2024) · Globecom · doi:10.1109/globecom52923.2024.10901140 · Cited by 5
“Among these DP-FL frameworks, FL with localized DP has become the de facto standard [7, 8], which focuses on protecting of participants’ gradients and parameters.”
High-Dimensional Data Release With Local Differential Privacy Under IoT Architecture
Ye, X., Yang, G., Deng, H., Jie, P., Wu, R., & Jiang, H. L. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3590759 · Cited by 5
“Both have been widely used in many fields, such as IoT [12], federated learning [13], [14], data mining and publishing [15], [16], and deep adversarial learning [17].”
IMFL: An Incentive Mechanism for Federated Learning With Personalized Protection
Li, M., Tian, Y., Zhang, J., Zhou, Z., Zhao, D., & Ma, J. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3387973 · Cited by 5
“Previous works on DP [14], [15] have primarily focused on privacy protection against attackers, neglecting data utility.”
BackgroundA Comprehensive Survey of Federated Open-World Learning
Cai, Z., Pang, J., Li, Y., Huang, Y., & Xie, Z. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3582580 · Cited by 4
“Unsupervised Domain Adaptation (UDA): Another strategy for enhancing generalization across domains is unsupervised domain adaptation (UDA), which exploits unlabeled samples from both the source and target distributions when target labels are unavailable [40], [41].”
Zhang, R., Ni, W., Fu, N., Hou, L., Zhang, D., Zhang, Y., & Zheng, L. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3602228 · Cited by 4
“2) Baselines and Implementation: a) Baselines: We compare PCFed-LDP against five representative clustered FL baselines under LDP: DCFL [5], ACS-FL [21], PACFL [43], CFL [3], and a variant PCFed-LDPN, which replaces ANAM with standard Gaussian noise addition.”
InfluentialTrindade, S., & da Fonseca, N. L. S. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3660648 · Cited by 5
“Multiple methods have been suggested to improve privacy and security in FL, such as clustering-based techniques [50], [51].”
A two-phase approach for locally differentially private fuzzy co-clustering
Zhang, P., An, J., Cheng, X., Zhu, Y., Zhang, J., & Zhang, Z. (2025) · Information Sciences · doi:10.1016/j.ins.2025.122381 · Cited by 4
Wu, D., Wu, S., Rawat, D. B., & Luo, C. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3331985 · Cited by 4
Zhang, S., Zhu, J., Luo, E., Zhu, X., & Yang, Q. (2025) · Electronics · doi:10.3390/electronics14102074 · Cited by 3
“…Privacy Mechanism Data Utility [24] × None [25] × None [26] × None [27] None [28] None [31] × DP × [32] × DP × [33] × DP [34] × DP [37] × DP [38] × Localized DP DPCK (Ours) Adaptive DP Note: Computational overhead: × = no optimization; (cid:88) = moderate optimization; = significant…”
Sun, B., Tu, Y., & Song, X. (2025) · Future Generation Computer Systems · doi:10.1016/j.future.2025.108005 · Cited by 4
Digital Twin-Enabled Edge Federated Learning for Data Streams
Xie, Z., Pang, J., Huang, Y., Balogun, O., Yu, D., & Cai, Z. (2026) · Tsinghua Science & Technology · doi:10.26599/tst.2024.9010227 · Cited by 3
Khalil, A., Delouee, M. L., Degeler, V., Mcuser, T., Anta, A. F., & Koldehofe, B. (2024) · Mediterranean Communication and Computer Networking Conference (MedComNet) · doi:10.1109/medcomnet62012.2024.10578208 · Cited by 3
“This approach reduces communication requirements between clients and the central server, as most of the data exchange for training occurs within clusters [7].”
Wang, Y., Zhang, Z., Qian, H., Gao, Y., & Wang, Q. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650346 · Cited by 3
“Consequently, we advocate for the adoption of differential privacy technology [6]–[8] as a robust solution for privacy preservation.”
BackgroundFedBS: Solving data heterogeneity issue in federated learning using balanced subtasks
Su, C., Wu, J., Zhang, R., Kang, Z., Xia, H., & Zhang, C. (2025) · High-Confidence Computing · doi:10.1016/j.hcc.2025.100322 · Cited by 3
Zhang, P., Zhang, Y., Wang, Z., Zhang, Q., & Gu, Z. (2025) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-025-02116-3 · Cited by 3
“Some existing works use DP to protect privacy for federated learning, such as [22–24 ].”
Liu, J., Luo, X., Zhao, Z., Chang, Z., Pan, M., Li, P., Min, G., & Li, H. (2024) · International Conference on Communications · doi:10.1109/icc51166.2024.10622682 · Cited by 3
“Recent studies [7]–[9] apply DP to FL, in the FL local model training stage, they inject corresponding Gaussian noise into the derived gradients to prevent privacy leakage.”
BackgroundFair Collaborative Learning (FairCL): A Method to Improve Fairness amid Personalization
Lin, F., Zhao, C., Qian, X., Vehik, K., & Huang, S. (2024) · INFORMS Journal on Data Science · doi:10.1287/ijds.2024.0029 · Cited by 5
Tpfl: tsetlin-personalized federated learning with confidence-based clustering
Gohari, R. J., Aliahmadipour, L., & Valipour, E. (2025) · Cluster Computing · doi:10.1007/s10586-025-05292-2 · Cited by 5
“This inherent voting scheme provides a unique capability for calculating the confidence score–the higher the vote margin, the more confident the TM is in its prediction for a certain class.”
Liu, T., Wu, H., Sun, X., Niu, C., & Yin, H. (2024) · Electronics · doi:10.3390/electronics13214187 · Cited by 2
GVFL: A group-verifiable federated learning with privacy
Ma, J., Qing, X., Xu, X., & Chen, Y. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103403 · Cited by 2
SFLES: Shuffled differentially private federated learning with early-stopping strategy
Li, Y., Huang, C., Zhao, Y., Du, X., Huang, J., & Yuan, Y. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129970 · Cited by 2
Differential Privacy-Based Adaptive Sparse Federated Learning in UAV Networks
Chen, Z., Du, J., Jiang, C., Hou, X., Han, Z., & Poor, H. V. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3644438 · Cited by 2
“This exposure not only increases the risk of unintended data leakage but also enables possible reconstruction of the original data, as sensitive patterns and attributes from the local datasets may be inferred during model updates [43], [44].”
Yang, L., Li, S., & Zhu, C. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104393 · Cited by 2
A systematic survey on clustering in federated learning
Belfeki, Z., Krichen, M., & Zidi, S. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21541-x · Cited by 2
EPFed: Achieving Optimal Balance between Privacy and Efficiency in Federated Learning
Mao, D., Yang, Q., Wang, H., Chen, Z., Li, C., Song, Y., & Qin, Z. (2024) · Electronics · doi:10.3390/electronics13061028 · Cited by 4
Fair and Communication-Efficient Personalized Federated Learning
Zheng, Y., Zheng, X., Wang, T., Mu, C., & Zhakiyev, N. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-71467-2_10 · Cited by 2
Privacy-Preserving Parameter Aggregation Scheme Based on Two Leaders for Federated Learning
Wang, W., Lian, Z., Li, T., Sakurai, K., & Su, C. (2024) · IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) · doi:10.1109/cyberscitech64112.2024.00029 · Cited by 3
“For example, He et al. [8] proposed a local differential privacy scheme to enhance security in heterogeneous IoT environments.”
QoE‐based dynamic resource allocation for heterogeneous smart distribution grids
Li, Y., Huo, Y., Zhou, Z., Gao, Q., Tao, J., Yan, T., & Xiao, S. (2025) · IET Communications · doi:10.1049/cmu2.70001 · Cited by 2
Morafah, M., Chang, H., & Lin, B. (2024) · doi:10.1145/3676536.3697130 · Cited by 2
“Moreover, some studies proposed data sharing or augmentation techniques to bring local data distributions closer to one another [13, 21, 35, 41, 46, 56, 59].”
Online Personalized Federated Learning Methods for Intrusion Detection in Dynamic UAV Networks
Cui, X., Wu, J., Fan, X., Yu, Q., Wang, T., Li, G., & Luo, C. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-8725-1_32 · Cited by 2
The Client-Level GAN-Based Data Reconstruction Attack and Defense in Clustered Federated Learning
Wu, H., Shi, L., Ye, J., Fan, Y., & Lv, Z. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-71464-1_38 · Cited by 1
Shen, F., Hui, L., Liang, Q., Zhang, J., Xu, C., Chen, Y., & He, Y. (2024) · International Conference on System Reliability and Safety Engineering (SRSE) · doi:10.1109/srse63568.2024.10772491 · Cited by 1
Chen, Z., Zhang, M., Mostyn, C., Jiang, H., & Feng, X. (2024) · IEEE International Performance, Computing, and Communications Conference · doi:10.1109/ipccc59868.2024.10850041 · Cited by 1
“In the first strategy, the goal can be achieved by model norm clipping [4, 5], gradient sparsification and quantization [6– 8], and differential privacy [9, 10].”
Guo, N., Pan, Y., & Yang, Y. (2024) · International Conference on Communication and Network Security (ICCNS) · doi:10.1145/3711618.3711641 · Cited by 1
Sun, Q., & Yang, G. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3595094 · Cited by 1
“W ITH the rapid advancement of information technology, the Internet of Things (IoT) has achieved ubiquitous interconnection among humans, machines, and objects, thereby supporting data collection, resource sharing, intelligent analysis, and collaborative management [1], [2], [3].”
Sasirekha, B., & Gunavathi, C. (2025) · IEEE Access · doi:10.1109/access.2025.3596974 · Cited by 1
“In this paper [60] author introduced ACS-FL (Adaptive Clipping weight compression and parameter Shuffling) to train a local differentially private FL model on heterogeneous IoT data, where adaptive clipping and parameter shuffling are used to balance privacy and accuracy while reducing the…”
Yang, L., Wang, X., & Jiao, Y. (2025) · Sustainability · doi:10.3390/su17209020 · Cited by 1
Mukherjee, A., Chae, J., & Rani, M. J. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3644428 · Cited by 1
“Utilization of reinforcement learning and deep neural networks has demonstrated improved detection rates for various security breaches, including SSDF and jamming attacks [22], [23], [24], [25].”
Trindade, S., & da Fonseca, N. L. S. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3679270 · Cited by 1
“Variousmethods enhance privacy and security in FL. Clustering-based approaches enable privacy-preserving grouping via gradient obfuscation or encoded representations while [32], [33], and improve robustness through anomaly detection [34], [35].”
Efficient state change detection method for modeling stateful time series data
Liu, X., Luo, R., Li, W., & Bi, Q. (2024) · International Journal of Robust and Nonlinear Control · doi:10.1002/rnc.7499 · Cited by 1
Enhancing Federated Learning in IoT Through Dynamic Spectral Clustering
Zheng, C., Gong, J., Guo, J., Tang, Z., & Wang, T. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-8728-2_15 · Cited by 1
Khan, M. A., Rais, R. N. B., Khalid, O., & Bilal, K. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-95133-6_5 · Cited by 1
Byzantine-Robust Federated Learning Based on Blockchain
Song, L., Cai, C., Wei, S., Banerjee, R., Feng, X., & Jiang, H. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-71464-1_39
A Method for Abnormal Detection and Poisoned Data Recovery in Clustered Federated Learning
Chen, Y., Shi, L., Xu, H., Ye, J., & Xu, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-71467-2_4
FedDAGC: Dynamic Adaptive Graph Coarsening for Federated Learning on Non-IID Graphs
Zhang, C., & Hu, C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-71467-2_5
PDTV-FEL: privacy-preserving and dual traceable verification federated edge learning
Zhang, P., Xu, L., Xu, C., Mei, L., & Ni, Y. (2026) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-026-03138-w
Metadata
- Authors
- He, Z., Wang, L., & Cai, Z.
- Affiliations
- Jinan University (CN)
- Georgia State University (US)
- Venue
- IEEE Internet of Things Journal
- Published
- 2024-01-01
- Volume
- 11
- Issue
- 1
- Pages
- 137-146
- ISSN
- 2327-4662 (ISSN-L)
- 2372-2541
- OpenAlex
- W4385627109
- Cited by
- 143
- References
- 48
- Citations by year
- 2026: 35 · 2025: 55 · 2024: 48
- FWCI
- 12.66
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Internet of Things Journal (publishedVersion)
- Funders
- Guangzhou Basic and Applied Basic Research Project (SL2022A04J01519)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Artificial Intelligence › Internet Traffic Analysis and Secure E-voting
- Physical Sciences › Computer Science › Computer Networks and Communications › Cryptography and Data Security
- Keywords
- federated learning, local differential privacy, Internet of Things, data heterogeneity, clustering, adaptive clipping, weight compression, privacy-utility trade-off, inference attacks, communication overhead
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
