{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T12:04:57Z","timestamp":1779883497759,"version":"3.53.1"},"reference-count":17,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12501634"],"award-info":[{"award-number":["12501634"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62562006"],"award-info":[{"award-number":["62562006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004607","name":"Guangxi Natural Science Foundation","doi-asserted-by":"publisher","award":["2025GXNSFHA069193"],"award-info":[{"award-number":["2025GXNSFHA069193"]}],"id":[{"id":"10.13039\/501100004607","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004607","name":"Guangxi Natural Science Foundation","doi-asserted-by":"publisher","award":["2024GXNSFAA010242"],"award-info":[{"award-number":["2024GXNSFAA010242"]}],"id":[{"id":"10.13039\/501100004607","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015920","name":"Guangxi University of Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100015920","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Systems Architecture"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.sysarc.2026.103790","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T15:09:25Z","timestamp":1774883365000},"page":"103790","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["AdaScaleDP: An adaptive and scale-aware differential privacy aggregation framework for federated learning"],"prefix":"10.1016","volume":"176","author":[{"given":"Huan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2009-5435","authenticated-orcid":false,"given":"Chenxi","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaoming","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2790-8285","authenticated-orcid":false,"given":"Jianhua","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shufa","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziheng","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.sysarc.2026.103790_b1","series-title":"2021 IEEE Symposium on Security and Privacy","first-page":"3","article-title":"Membership inference attacks against machine learning models","author":"Shokri","year":"2021"},{"key":"10.1016\/j.sysarc.2026.103790_b2","series-title":"30th USENIX Security Symposium","first-page":"2633","article-title":"Extracting training data from large language models","author":"Carlini","year":"2021"},{"issue":"3\u20134","key":"10.1016\/j.sysarc.2026.103790_b3","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":"10.1016\/j.sysarc.2026.103790_b4","series-title":"ACM SIGSAC Conference on Computer and Communications Security","first-page":"308","article-title":"Deep learning with differential privacy","author":"Abadi","year":"2016"},{"key":"10.1016\/j.sysarc.2026.103790_b5","series-title":"ACM SIGSAC Conference on Computer and Communications Security","first-page":"1054","article-title":"RAPPOR: randomized aggregatable privacy-preserving ordinal response","author":"Erlingsson","year":"2014"},{"key":"10.1016\/j.sysarc.2026.103790_b6","series-title":"Annual International Conference on the Theory and Applications of Cryptographic Techniques","first-page":"486","article-title":"Our data, ourselves: privacy via distributed noise generation","author":"Dwork","year":"2006"},{"key":"10.1016\/j.sysarc.2026.103790_b7","series-title":"14th USENIX Symposium on Networked Systems Design and Implementation","first-page":"259","article-title":"Prio: private, robust, and scalable computation of aggregate statistics","author":"Corrigan-Gibbs","year":"2017"},{"issue":"1","key":"10.1016\/j.sysarc.2026.103790_b8","first-page":"86","article-title":"Dprio: efficient differential privacy for prio","volume":"2023","author":"Keeler","year":"2023","journal-title":"Proc. Priv. Enhancing Technol."},{"key":"10.1016\/j.sysarc.2026.103790_b9","series-title":"ACM SIGSAC Conference on Computer and Communications Security","first-page":"2574","article-title":"Sampleable anonymous aggregation for private federated data analysis","author":"Talwar","year":"2023"},{"issue":"5","key":"10.1016\/j.sysarc.2026.103790_b10","first-page":"1","article-title":"Adaptive privacy-preserving deep learning with Byzantine robustness","volume":"18","author":"Liu","year":"2020","journal-title":"IEEE Trans. Dependable Secur. Comput."},{"key":"10.1016\/j.sysarc.2026.103790_b11","series-title":"2019 IEEE Symposium on Security and Privacy","first-page":"332","article-title":"Differentially private model publishing for deep learning","author":"Yu","year":"2019"},{"issue":"1","key":"10.1016\/j.sysarc.2026.103790_b12","first-page":"5","article-title":"Prio+: Privacy preserving aggregate statistics via boolean shares","volume":"2023","author":"Addanki","year":"2023","journal-title":"Proc. Priv. Enhancing Technol."},{"issue":"4","key":"10.1016\/j.sysarc.2026.103790_b13","first-page":"5","article-title":"Bounding data reconstruction attacks with the hypothesis testing interpretation of differential privacy","volume":"2023","author":"Kaissis","year":"2023","journal-title":"Proc. Priv. Enhancing Technol."},{"key":"10.1016\/j.sysarc.2026.103790_b14","series-title":"Proceedings of the 39th International Conference on Machine Learning","first-page":"8056","article-title":"Bounding training data reconstruction in private learning","volume":"162","author":"Guo","year":"2022"},{"key":"10.1016\/j.sysarc.2026.103790_b15","series-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","first-page":"1196","article-title":"Machine learning with adversaries: Byzantine tolerant gradient descent","author":"Blanchard","year":"2017"},{"key":"10.1016\/j.sysarc.2026.103790_b16","series-title":"Advances in Neural Information Processing Systems 34 (NeurIPS 2021)","first-page":"17455","article-title":"Differentially private learning with adaptive clipping","author":"Andrew","year":"2021"},{"key":"10.1016\/j.sysarc.2026.103790_b17","series-title":"Proceedings on Privacy Enhancing Technologies Symposium","article-title":"Differentially private federated quantiles with the distributed discrete gaussian mechanism","author":"Pillutla","year":"2022"}],"container-title":["Journal of Systems Architecture"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1383762126001086?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1383762126001086?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T11:10:57Z","timestamp":1779880257000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1383762126001086"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":17,"alternative-id":["S1383762126001086"],"URL":"https:\/\/doi.org\/10.1016\/j.sysarc.2026.103790","relation":{},"ISSN":["1383-7621"],"issn-type":[{"value":"1383-7621","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"AdaScaleDP: An adaptive and scale-aware differential privacy aggregation framework for federated learning","name":"articletitle","label":"Article Title"},{"value":"Journal of Systems Architecture","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.sysarc.2026.103790","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":"103790"}}