{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T17:44:09Z","timestamp":1767980649995,"version":"3.49.0"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"22","license":[{"start":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T00:00:00Z","timestamp":1763164800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T00:00:00Z","timestamp":1763164800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T00:00:00Z","timestamp":1763164800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476095"],"award-info":[{"award-number":["62476095"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001321","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["2025A1515011525"],"award-info":[{"award-number":["2025A1515011525"]}],"id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2025,11,15]]},"DOI":"10.1109\/jiot.2025.3600099","type":"journal-article","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:46:41Z","timestamp":1755546401000},"page":"47288-47306","source":"Crossref","is-referenced-by-count":1,"title":["FedMAR: A Privacy-Preserving and Robust Server-Side Multistage Federated Learning"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4233-5385","authenticated-orcid":false,"given":"Leyu","family":"Shi","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8925-8192","authenticated-orcid":false,"given":"Ying","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6278-120X","authenticated-orcid":false,"given":"Chong","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0648-3405","authenticated-orcid":false,"given":"Siquan","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5708-9518","authenticated-orcid":false,"given":"Jiafeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4952-699X","authenticated-orcid":false,"given":"Xiping","family":"Hu","sequence":"additional","affiliation":[{"name":"Guangdong–Hong Kong–Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing and the Artificial Intelligence Research Institute, Shenzhen MSU-BIT University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3529-2640","authenticated-orcid":false,"given":"Victor C. M.","family":"Leung","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054676"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3219617.3219655"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3173996"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3305873"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3293417"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3315125"},{"key":"ref7","first-page":"312","article-title":"Unsupervised label noise modeling and loss correction","volume-title":"Proc. 36th Int. Conf. Mach. Learn. (ICML)","author":"Arazo"},{"key":"ref8","first-page":"1","article-title":"DivideMix: Learning with noisy labels as semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Rep.","author":"Li"},{"key":"ref9","first-page":"1","article-title":"Part-dependent label noise: Towards instance-dependent label noise","volume-title":"Proc. Neural Inf. Process. Syst. (NeurIPS)","author":"Xia"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446170"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3080522"},{"key":"ref12","first-page":"6357","article-title":"Ditto: Fair and robust federated learning through personalization","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Li"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3298606"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CSF.2017.11"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2021.3067794"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3163397"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00500"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3168556"},{"key":"ref19","first-page":"1","article-title":"Analyzing federated learning through an adversarial lens","volume-title":"Proc. Int. Conf. Learn. Rep. (ICML)","author":"Arjun"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3128646"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3023126"},{"key":"ref22","first-page":"1","article-title":"DBA: Distributed Backdoor attacks against federated learning","volume-title":"Proc. Int. Conf. Learn. Rep. (ICLR)","author":"Xie"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00034"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01456"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS47876.2019.00042"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3108434"},{"key":"ref27","first-page":"5650","article-title":"Byzantine-robust distributed learning: Towards optimal statistical rates","volume-title":"Proc. Int. Conf. Learn. Rep. (ICML)","author":"Yin"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00994"},{"key":"ref29","first-page":"9","article-title":"The limitations of federated learning in Sybil settings","volume-title":"Proc. Symp. Res. Attacks Intrusion Defenses","author":"Fung"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3288886"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3249568"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00786"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01571"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3147508"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00981"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00989"},{"key":"ref37","first-page":"61","article-title":"Membership inference attack against differentially private deep learning model","volume":"11","author":"Rahman","year":"2018","journal-title":"Trans. Data Privacy"},{"key":"ref38","first-page":"16937","article-title":"Inverting gradients\u2014How easy is it to break privacy in federated learning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Geiping"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01607"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3196646"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00919"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.12"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3185770"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3306159"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3176360"},{"key":"ref46","first-page":"1709","article-title":"QSGD: Communication-efficient SGD via gradient Quantization and encoding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Alistarh"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00220"},{"key":"ref48","first-page":"1","article-title":"TernGrad: Ternary gradients to reduce communication in distributed deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Wen"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3137321"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3056991"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3453031"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ISCTIS58954.2023.10213128"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3233580"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2017.2787987"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2987958"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3057653"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3140806"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2022.3144699"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2023.3264697"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20825"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i21.34360"},{"key":"ref62","volume-title":"Exploring federated pruning for large language models","author":"Guo","year":"2025"},{"key":"ref63","first-page":"1","article-title":"FedPAQ: A communication-efficient federated learning method with periodic averaging and Quantization","volume-title":"Proc. 23rd Int. Conf. Artif. Intell. Stat.","author":"Reisizadeh"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3638252"},{"key":"ref65","first-page":"6","article-title":"Personalized federated learning with first order model optimization","volume-title":"Proc. Int. Conf. Learn. Rep.","author":"Zhang"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3533899"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3581555"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2023.3320758"},{"key":"ref69","article-title":"MetaLR: Layer-wise learning rate based on Meta-learning for adaptively fine-tuning medical pre-trained models","author":"Chen","year":"2022","journal-title":"arxiv.2206.01408"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3216454"},{"key":"ref71","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Stat. (AISTATS)","volume":"54","author":"McMahan"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3090331"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CSCI.2016.0225"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref77","first-page":"1","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","volume-title":"Proc. Conf. Empirical Methods Nat. Lang. Process.","author":"Richard"},{"key":"ref78","first-page":"1","article-title":"DeBERTaV3: Improving DeBERTa using ELECTRA-style pre-training with gradient-disentangled embedding sharing","volume-title":"Proc. Int. Conf. Learn. Rep. (ICLR)","author":"He"},{"key":"ref79","volume-title":"Measuring the effects of non-identical data distribution for federated visual classification","author":"Hsu","year":"2019"},{"key":"ref80","first-page":"1","article-title":"The hidden vulnerability of distributed learning in Byzantium","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Mhamdi"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02352"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1561\/9781601988195"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref84","first-page":"9","article-title":"Scalable private learning with PATE","volume-title":"Proc. Int. Conf. Learn. Rep. (ICLR)","author":"Papernot"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11231115\/11129099.pdf?arnumber=11129099","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T18:12:02Z","timestamp":1762539122000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11129099\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":84,"journal-issue":{"issue":"22"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2025.3600099","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,15]]}}}