{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T14:23:32Z","timestamp":1780410212101,"version":"3.54.1"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100013066","name":"Key Scientific Research Project of Colleges and Universities in Henan Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013066","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Future Generation Computer Systems"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.future.2026.108554","type":"journal-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T00:40:51Z","timestamp":1777941651000},"page":"108554","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Research on differentially private federated learning based on dynamic gradient clipping and layer-wise perturbation mechanisms"],"prefix":"10.1016","volume":"183","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9007-3267","authenticated-orcid":false,"given":"Peiqian","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihao","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"6","key":"10.1016\/j.future.2026.108554_b1","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1109\/MCOM.2008.4539481","article-title":"A tutorial survey on vehicular ad hoc networks","volume":"46","author":"Hartenstein","year":"2008","journal-title":"IEEE Commun. Mag."},{"issue":"5","key":"10.1016\/j.future.2026.108554_b2","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1109\/JIOT.2016.2579198","article-title":"Edge computing: Vision and challenges","volume":"3","author":"Shi","year":"2016","journal-title":"IEEE Internet Things J."},{"issue":"1\u20132","key":"10.1016\/j.future.2026.108554_b3","first-page":"1","article-title":"Advances and open problems in federated learning","volume":"14","author":"Kairouz","year":"2021","journal-title":"Found. Trends\u00ae Mach. Learn."},{"key":"10.1016\/j.future.2026.108554_b4","series-title":"Artificial Intelligence and Statistics","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017"},{"issue":"1","key":"10.1016\/j.future.2026.108554_b5","doi-asserted-by":"crossref","first-page":"52","DOI":"10.70589\/JRTCSE.2023.1.8","article-title":"Enhancing mobile data security with zero-trust architecture and federated learning: A comprehensive approach to prevent data leakage on smart terminals","volume":"11","author":"Yenugula","year":"2023","journal-title":"J. Recent. Trends Comput. Sci. Eng. (JRTCSE)"},{"issue":"3\u20134","key":"10.1016\/j.future.2026.108554_b6","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\u00ae Theor. Computer Sci."},{"key":"10.1016\/j.future.2026.108554_b7","doi-asserted-by":"crossref","unstructured":"Matt Fredrikson, Somesh Jha, Thomas Ristenpart, Model inversion attacks that exploit confidence information and basic countermeasures, in: Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security, 2015, pp. 1322\u20131333.","DOI":"10.1145\/2810103.2813677"},{"key":"10.1016\/j.future.2026.108554_b8","series-title":"2019 IEEE Symposium on Security and Privacy","first-page":"739","article-title":"Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning","author":"Nasr","year":"2019"},{"key":"10.1016\/j.future.2026.108554_b9","doi-asserted-by":"crossref","unstructured":"Briland Hitaj, Giuseppe Ateniese, Fernando Perez-Cruz, Deep models under the GAN: Information leakage from collaborative deep learning, in: Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, 2017, pp. 603\u2013618.","DOI":"10.1145\/3133956.3134012"},{"key":"10.1016\/j.future.2026.108554_b10","series-title":"2017 IEEE Symposium on Security and Privacy","first-page":"3","article-title":"Membership inference attacks against machine learning models","author":"Shokri","year":"2017"},{"key":"10.1016\/j.future.2026.108554_b11","doi-asserted-by":"crossref","unstructured":"Reza Shokri, Vitaly Shmatikov, Privacy-preserving deep learning, in: Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security, 2015, pp. 1310\u20131321.","DOI":"10.1145\/2810103.2813687"},{"key":"10.1016\/j.future.2026.108554_b12","series-title":"Differentially private federated learning: A client level perspective","author":"Geyer","year":"2017"},{"key":"10.1016\/j.future.2026.108554_b13","series-title":"ICC 2019-2019 IEEE International Conference on Communications","first-page":"1","article-title":"Towards efficient and privacy-preserving federated deep learning","author":"Hao","year":"2019"},{"key":"10.1016\/j.future.2026.108554_b14","doi-asserted-by":"crossref","unstructured":"Martin Abadi, Andy Chu, Ian Goodfellow, H Brendan McMahan, Ilya Mironov, Kunal Talwar, Li Zhang, Deep learning with differential privacy, in: Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, 2016, pp. 308\u2013318.","DOI":"10.1145\/2976749.2978318"},{"key":"10.1016\/j.future.2026.108554_b15","doi-asserted-by":"crossref","unstructured":"Ning Wang, Yang Xiao, Yimin Chen, Ning Zhang, Wenjing Lou, Y Thomas Hou, Squeezing more utility via adaptive clipping on differentially private gradients in federated meta-learning, in: Proceedings of the 38th Annual Computer Security Applications Conference, 2022, pp. 647\u2013657.","DOI":"10.1145\/3564625.3564652"},{"key":"10.1016\/j.future.2026.108554_b16","series-title":"2021 IEEE International Conference on Big Data (Big Data)","first-page":"1172","article-title":"Resisting distributed backdoor attacks in federated learning: A dynamic norm clipping approach","author":"Guo","year":"2021"},{"issue":"1","key":"10.1016\/j.future.2026.108554_b17","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1111\/rssb.12454","article-title":"Gaussian differential privacy","volume":"84","author":"Dong","year":"2022","journal-title":"J. R. Stat. Soc. Ser. B Stat. Methodol."},{"key":"10.1016\/j.future.2026.108554_b18","doi-asserted-by":"crossref","unstructured":"Haolin Liu, Chenyu Li, Bochao Liu, Pengju Wang, Shiming Ge, Weiping Wang, Differentially private learning with grouped gradient clipping, in: Proceedings of the 3rd ACM International Conference on Multimedia in Asia, 2021, pp. 1\u20137.","DOI":"10.1145\/3469877.3490594"},{"key":"10.1016\/j.future.2026.108554_b19","first-page":"17455","article-title":"Differentially private learning with adaptive clipping","volume":"34","author":"Andrew","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"3","key":"10.1016\/j.future.2026.108554_b20","first-page":"2975","article-title":"Privacy-preserving multi-granular federated neural architecture search\u2013a general framework","volume":"35","author":"Pan","year":"2021","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.future.2026.108554_b21","doi-asserted-by":"crossref","first-page":"952","DOI":"10.1109\/TIFS.2020.3025438","article-title":"An automatic cost learning framework for image steganography using deep reinforcement learning","volume":"16","author":"Tang","year":"2020","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"issue":"6","key":"10.1016\/j.future.2026.108554_b22","first-page":"2969","article-title":"NPMML: A framework for non-interactive privacy-preserving multi-party machine learning","volume":"18","author":"Li","year":"2020","journal-title":"IEEE Trans. Dependable Secur. Comput."},{"key":"10.1016\/j.future.2026.108554_b23","series-title":"Adaclip: Adaptive clipping for private SGD","author":"Pichapati","year":"2019"},{"key":"10.1016\/j.future.2026.108554_b24","series-title":"Three tools for practical differential privacy","author":"van der Veen","year":"2018"},{"key":"10.1016\/j.future.2026.108554_b25","doi-asserted-by":"crossref","first-page":"3454","DOI":"10.1109\/TIFS.2020.2988575","article-title":"Federated learning with differential privacy: Algorithms and performance analysis","volume":"15","author":"Wei","year":"2020","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.future.2026.108554_b26","unstructured":"Dongsheng Yu, Huishuai Zhang, Wei Chen, Improve the gradient perturbation approach for differentially private optimization, in: NeurIPS 2018 Workshop, 2018."},{"key":"10.1016\/j.future.2026.108554_b27","series-title":"Dynamic differential-privacy preserving SGD","author":"Du","year":"2021"},{"key":"10.1016\/j.future.2026.108554_b28","article-title":"Adaptive clipping for differential private federated learning in interpolation regimes","author":"Fukami","year":"2025","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.future.2026.108554_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.comnet.2025.111139","article-title":"Differential private federated learning with per-sample adaptive clipping and layer-wise gradient perturbation","volume":"261","author":"Yuan","year":"2025","journal-title":"Comput. Netw."},{"key":"10.1016\/j.future.2026.108554_b30","series-title":"Mitigating disparate impact of differentially private learning through bounded adaptive clipping","author":"Zhao","year":"2025"},{"key":"10.1016\/j.future.2026.108554_b31","series-title":"Theory of Cryptography Conference","first-page":"635","article-title":"Concentrated differential privacy: Simplifications, extensions, and lower bounds","author":"Bun","year":"2016"},{"key":"10.1016\/j.future.2026.108554_b32","series-title":"2017 IEEE 30th Computer Security Foundations Symposium","first-page":"263","article-title":"R\u00e9nyi differential privacy","author":"Mironov","year":"2017"},{"key":"10.1016\/j.future.2026.108554_b33","series-title":"48th Annual IEEE Symposium on Foundations of Computer Science","first-page":"94","article-title":"Mechanism design via differential privacy","author":"McSherry","year":"2007"},{"key":"10.1016\/j.future.2026.108554_b34","doi-asserted-by":"crossref","unstructured":"Frank D. McSherry, Privacy integrated queries: an extensible platform for privacy-preserving data analysis, in: Proceedings of the 2009 ACM SIGMOD International Conference on Management of Data, 2009, pp. 19\u201330.","DOI":"10.1145\/1559845.1559850"},{"key":"10.1016\/j.future.2026.108554_b35","article-title":"Deep leakage from gradients","volume":"32","author":"Zhu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.future.2026.108554_b36","first-page":"16937","article-title":"Inverting gradients-how easy is it to break privacy in federated learning?","volume":"33","author":"Geiping","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"8","key":"10.1016\/j.future.2026.108554_b37","doi-asserted-by":"crossref","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","article-title":"Representation learning: A review and new perspectives","volume":"35","author":"Bengio","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.future.2026.108554_b38","article-title":"MNIST handwritten digit database","author":"Yann","year":"2010","journal-title":"ATT Labs."},{"key":"10.1016\/j.future.2026.108554_b39","series-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"10.1016\/j.future.2026.108554_b40","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.future.2026.108554_b41","series-title":"Learning differentially private recurrent language models","author":"McMahan","year":"2017"},{"key":"10.1016\/j.future.2026.108554_b42","doi-asserted-by":"crossref","first-page":"41727","DOI":"10.52202\/075280-1808","article-title":"Automatic clipping: Differentially private deep learning made easier and stronger","volume":"36","author":"Bu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Future Generation Computer Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167739X26001883?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167739X26001883?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T13:44:46Z","timestamp":1780407886000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167739X26001883"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":42,"alternative-id":["S0167739X26001883"],"URL":"https:\/\/doi.org\/10.1016\/j.future.2026.108554","relation":{},"ISSN":["0167-739X"],"issn-type":[{"value":"0167-739X","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Research on differentially private federated learning based on dynamic gradient clipping and layer-wise perturbation mechanisms","name":"articletitle","label":"Article Title"},{"value":"Future Generation Computer Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.future.2026.108554","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108554"}}