{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T04:49:09Z","timestamp":1782362949056,"version":"3.54.5"},"reference-count":37,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T00:00:00Z","timestamp":1700524800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Science and Technology Research Planning Project of Jilin Provincial Department of Education in China","award":["JJKH20230766KJ"],"award-info":[{"award-number":["JJKH20230766KJ"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>There are several unsolved problems in federated learning, such as the security concerns and communication costs associated with it. Differential privacy (DP) offers effective privacy protection by introducing noise to parameters based on rigorous privacy definitions. However, excessive noise addition can potentially compromise the accuracy of the model. Another challenge in federated learning is the issue of high communication costs. Training large-scale federated models can be slow and expensive in terms of communication resources. To address this, various model pruning algorithms have been proposed. To address these challenges, this paper introduces a communication-efficient, privacy-preserving FL algorithm based on two-stage gradient pruning and differentiated differential privacy, named IsmDP-FL. The algorithm leverages a two-stage approach, incorporating gradient pruning and differentiated differential privacy. In the first stage, the trained model is subject to gradient pruning, followed by the addition of differential privacy to the important parameters selected after pruning. Non-important parameters are pruned by a certain ratio, and differentiated differential privacy is applied to the remaining parameters in each network layer. In the second stage, gradient pruning is performed during the upload to the server for aggregation, and the final result is returned to the client to complete the federated learning process. Extensive experiments demonstrate that the proposed method ensures a high communication efficiency, maintains the model privacy, and reduces the unnecessary use of the privacy budget.<\/jats:p>","DOI":"10.3390\/s23239305","type":"journal-article","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T12:12:13Z","timestamp":1700568733000},"page":"9305","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["A Communication-Efficient, Privacy-Preserving Federated Learning Algorithm Based on Two-Stage Gradient Pruning and Differentiated Differential Privacy"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2907-9811","authenticated-orcid":false,"given":"Yong","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China"},{"name":"AI Research Institute, Changchun University of Technology, Changchun 130012, China"},{"name":"School of Computer Science and Technology, Jilin University, Changchun 130012, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4727-7488","authenticated-orcid":false,"given":"Wei","family":"Du","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liquan","family":"Han","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenjian","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tongtong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,11,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Lee, I. (2020). Internet of Things (IoT) cybersecurity: Literature review and IoT cyber risk management. Future Internet, 12.","DOI":"10.3390\/fi12090157"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Pajooh, H.H., Demidenko, S., Aslam, S., and Harris, M. (2022). Blockchain and 6G-Enabled IoT. Inventions, 7.","DOI":"10.3390\/inventions7040109"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Khan, Z.A., and Namin, A.S. (2022). A Survey of DDOS Attack Detection Techniques for IoT Systems Using BlockChain Technology. Electronics, 11.","DOI":"10.3390\/electronics11233892"},{"key":"ref_4","unstructured":"Hu, R., Gong, Y., and Guo, Y. (2022). Federated learning with sparsified model perturbation: Improving accuracy under client-level differential privacy. arXiv."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Wang, S., Valls, V., Ko, B.J., Lee, W.H., Leung, K.K., and Tassiulas, L. (2022). Model pruning enables efficient federated learning on edge devices. IEEE Trans. Neural Netw. Learn. Syst., Early Access.","DOI":"10.1109\/TNNLS.2022.3166101"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"22359","DOI":"10.1109\/ACCESS.2022.3151670","article-title":"Differential privacy for deep and federated learning: A survey","volume":"10","author":"Abdelhadi","year":"2022","journal-title":"IEEE Access"},{"key":"ref_7","unstructured":"Chamikara, M., Liu, D., Camtepe, S., Nepal, S., Grobler, M., Bert\u00f3k, P., and Khalil, I. (2022, January 26\u201330). Local differential privacy for federated learning in industrial settings. Proceedings of the Computer Security\u2014ESORICS 2022: 27th European Symposium on Research in Computer Security, Copenhagen, Denmark."},{"key":"ref_8","unstructured":"Heikkil\u00e4, M.A., Koskela, A., Shimizu, K., Kaski, S., and Honkela, A. (2020). Differentially private cross-silo federated learning. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Alasmary, H., and Tanveer, M. (2023). ESCI-AKA: Enabling Secure Communication in an IoT-Enabled Smart Home Environment Using Authenticated Key Agreement Framework. Mathematics, 11.","DOI":"10.3390\/math11163450"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Gupta, S., Alharbi, F., Alshahrani, R., Kumar Arya, P., Vyas, S., Elkamchouchi, D.H., and Soufiene, B.O. (2023). Secure and lightweight authentication protocol for privacy preserving communications in smart city applications. Sustainability, 15.","DOI":"10.3390\/su15065346"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Kanellopoulos, D., and Sharma, V.K. (2022). Dynamic load balancing techniques in the IoT: A review. Symmetry, 14.","DOI":"10.3390\/sym14122554"},{"key":"ref_12","unstructured":"Ma, X., Qin, M., Sun, F., Hou, Z., Yuan, K., Xu, Y., Wang, Y., Chen, Y.K., Jin, R., and Xie, Y. (2021). Effective model sparsification by scheduled grow-and-prune methods. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Ma, X., Zhang, J., Guo, S., and Xu, W. (2022, January 18\u201324). Layer-wised model aggregation for personalized federated learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00985"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"106775","DOI":"10.1016\/j.knosys.2021.106775","article-title":"A survey on federated learning","volume":"216","author":"Zhang","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"ref_15","first-page":"1773","article-title":"A Differential Privacy Protection Algorithm for Deep Neural Networks","volume":"44","author":"Zhou","year":"2022","journal-title":"J. Electron. Inf. Technol."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Yu, S., and Cui, L. (2022). Security and Privacy in Federated Learning, Springer.","DOI":"10.1007\/978-981-19-8692-5"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Habernal, I. (2021). When differential privacy meets NLP: The devil is in the detail. arXiv.","DOI":"10.18653\/v1\/2021.emnlp-main.114"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1561\/0400000042","article-title":"The algorithmic foundations of differential privacy","volume":"9","author":"Dwork","year":"2014","journal-title":"Found. Trends Theor. Comput. Sci."},{"key":"ref_19","unstructured":"Pihur, V., Korolova, A., Liu, F., Sankuratripati, S., Yung, M., Huang, D., and Zeng, R. (2018). Differentially-private \u201cdraw and discard\u201d machine learning. arXiv."},{"key":"ref_20","unstructured":"Geyer, R.C., Klein, T., and Nabi, M. (2017). Differentially private federated learning: A client level perspective. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Jiang, H., Gao, Y., Sarwar, S., GarzaPerez, L., and Robin, M. (2021, January 2\u20133). Differential privacy in privacy-preserving big data and learning: Challenge and opportunity. Proceedings of the Silicon Valley Cybersecurity Conference, San Jose, CA, USA.","DOI":"10.1007\/978-3-030-96057-5_3"},{"key":"ref_22","unstructured":"Xiao, Y., Xiong, L., Fan, L., and Goryczka, S. (2012). DPCube: Differentially private histogram release through multidimensional partitioning. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"797","DOI":"10.1007\/s00778-013-0309-y","article-title":"Differentially private histogram publication","volume":"22","author":"Xu","year":"2013","journal-title":"VLDB J."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Aziz, R., Banerjee, S., Bouzefrane, S., and Le Vinh, T. (2023). Exploring Homomorphic Encryption and Differential Privacy Techniques towards Secure Federated Learning Paradigm. Future Internet, 15.","DOI":"10.3390\/fi15090310"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"He, Z.B., Wang, L.T., and Cai, Z.P. (2023). Clustered federated learning with adaptive local differential privacy on heterogeneous iot data. IEEE Internet Things J., Early Access.","DOI":"10.1109\/JIOT.2023.3299947"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ozfatura, E., Ozfatura, K., and G\u00fcnd\u00fcz, D. (2021, January 12\u201320). Time-correlated sparsification for communication-efficient federated learning. Proceedings of the 2021 IEEE International Symposium on Information Theory (ISIT), IEEE, Online.","DOI":"10.1109\/ISIT45174.2021.9518221"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Gao, S., Huang, F., Cai, W., and Huang, H. (2021, January 20\u201325). Network pruning via performance maximization. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00915"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1109\/TSP.2023.3244092","article-title":"Joint privacy enhancement and quantization in federated learning","volume":"71","author":"Lang","year":"2023","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Jiang, X., and Borcea, C. (2023). Complement Sparsification: Low-Overhead Model Pruning for Federated Learning. arXiv.","DOI":"10.1609\/aaai.v37i7.25977"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Lin, R., Xiao, Y., Yang, T.J., Zhao, D., Xiong, L., Motta, G., and Beaufays, F. (2022). Federated pruning: Improving neural network efficiency with federated learning. arXiv.","DOI":"10.21437\/Interspeech.2022-10787"},{"key":"ref_31","first-page":"217","article-title":"Qsparse-local-SGD: Distributed SGD with quantization, sparsification and local computations","volume":"1","author":"Basu","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Aji, A.F., and Heafield, K. (2017). Sparse communication for distributed gradient descent. arXiv.","DOI":"10.18653\/v1\/D17-1045"},{"key":"ref_33","unstructured":"Liu, Y., Zhao, Y., Zhou, G., and Xu, K. (2021, January 8\u201312). FedPrune: Personalized and communication-efficient federated learning on non-IID data. Proceedings of the Neural Information Processing: 28th International Conference, ICONIP 2021, Bali, Indonesia. Part V 28."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Yu, S., Nguyen, P., Anwar, A., and Jannesari, A. (2023, January 1\u20134). Heterogeneous federated learning using dynamic model pruning and adaptive gradient. Proceedings of the 2023 IEEE\/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing (CCGrid), Bangalore, India.","DOI":"10.1109\/CCGrid57682.2023.00038"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"103039","DOI":"10.1016\/j.cose.2022.103039","article-title":"Preserving data privacy in federated learning through large gradient pruning","volume":"125","author":"Zhang","year":"2023","journal-title":"Comput. Secur."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Wei, W.J., Liu, L., Wut, Y.G., Su, G., and Iyengar, A. (2021, January 7\u201310). Gradient-leakage resilient federated learning. Proceedings of the 2021 IEEE 41st International Conference on Distributed Computing Systems (ICDCS), Washington, DC, USA.","DOI":"10.1109\/ICDCS51616.2021.00081"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Lomurno, E., Archetti, A., Cazzella, L., Samele, S., Di Perna, L., and Matteucci, M. (2022, January 23\u201325). SGDE: Secure generative data exchange for cross-silo federated learning. Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition, Xiamen, China.","DOI":"10.1145\/3573942.3573974"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/23\/9305\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:26:06Z","timestamp":1760131566000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/23\/9305"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,21]]},"references-count":37,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["s23239305"],"URL":"https:\/\/doi.org\/10.3390\/s23239305","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,21]]}}}