{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T22:06:02Z","timestamp":1743458762748,"version":"3.37.3"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1016\/j.ins.2024.121274","type":"journal-article","created":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T16:20:27Z","timestamp":1722442827000},"page":"121274","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":3,"special_numbering":"C","title":["FedNor: A robust training framework for federated learning based on normal aggregation"],"prefix":"10.1016","volume":"684","author":[{"given":"Shuo","family":"Xu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7326-5796","authenticated-orcid":false,"given":"Hui","family":"Xia","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4117-2656","authenticated-orcid":false,"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Peishun","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Fu","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.ins.2024.121274_br0010","series-title":"Proceedings of the 2019 IEEE International Conference on Image Processing","first-page":"101","article-title":"A new backdoor attack in CNNS by training set corruption without label poisoning","author":"Barni","year":"2019"},{"key":"10.1016\/j.ins.2024.121274_br0020","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/j.inffus.2022.09.011","article-title":"Survey on federated learning threats: concepts, taxonomy on attacks and defences, experimental study and challenges","volume":"90","author":"Barroso","year":"2023","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.ins.2024.121274_br0030","series-title":"Proceedings of the 32nd Annual Conference on Neural Information Processing Systems","first-page":"8632","article-title":"A little is enough: circumventing defenses for distributed learning","author":"Baruch","year":"2019"},{"key":"10.1016\/j.ins.2024.121274_br0040","series-title":"Proceedings of the 30th Annual Conference on Neural Information Processing Systems 2017","first-page":"119","article-title":"Machine learning with adversaries: byzantine tolerant gradient descent","author":"Blanchard","year":"2017"},{"key":"10.1016\/j.ins.2024.121274_br0050","series-title":"Proceedings of the 28th Annual Network and Distributed System Security Symposium","first-page":"1","article-title":"Fltrust: byzantine-robust federated learning via trust bootstrapping","author":"Cao","year":"2021"},{"author":"Chen","key":"10.1016\/j.ins.2024.121274_br0060"},{"key":"10.1016\/j.ins.2024.121274_br0070","series-title":"Proceedings of the 2018 ACM International Conference on Measurement and Modeling of Computer Systems","first-page":"96","article-title":"Distributed statistical machine learning in adversarial settings: byzantine gradient descent","author":"Chen","year":"2018"},{"key":"10.1016\/j.ins.2024.121274_br0080","series-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event","first-page":"2089","article-title":"Exploiting shared representations for personalized federated learning","volume":"vol. 139","author":"Collins","year":"2021"},{"key":"10.1016\/j.ins.2024.121274_br0090","series-title":"Proceedings of the 33rd Annual Conference on Neural Information Processing Systems 2020","article-title":"Personalized federated learning with Moreau envelopes","author":"Dinh","year":"2020"},{"issue":"2","key":"10.1016\/j.ins.2024.121274_br0100","doi-asserted-by":"crossref","first-page":"889","DOI":"10.1109\/TDSC.2023.3264697","article-title":"Privacy-preserving and byzantine-robust federated learning","volume":"21","author":"Dong","year":"2024","journal-title":"IEEE Trans. Dependable Secure Comput."},{"key":"10.1016\/j.ins.2024.121274_br0110","series-title":"Proceedings of the 37th AAAI Conference on Artificial Intelligence","first-page":"11800","article-title":"On the vulnerability of backdoor defenses for federated learning","author":"Fang","year":"2023"},{"author":"Fu","key":"10.1016\/j.ins.2024.121274_br0120"},{"key":"10.1016\/j.ins.2024.121274_br0130","doi-asserted-by":"crossref","first-page":"47230","DOI":"10.1109\/ACCESS.2019.2909068","article-title":"Badnets: evaluating backdooring attacks on deep neural networks","volume":"7","author":"Gu","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.ins.2024.121274_br0140","series-title":"Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"author":"Hinton","key":"10.1016\/j.ins.2024.121274_br0150"},{"key":"10.1016\/j.ins.2024.121274_br0160","unstructured":"Alex Krizhevsky, Geoffrey Hinton, et al., Learning multiple layers of features from tiny images, 2009."},{"issue":"11","key":"10.1016\/j.ins.2024.121274_br0170","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.ins.2024.121274_br0180","series-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event","first-page":"6357","article-title":"Ditto: fair and robust federated learning through personalization","volume":"vol. 139","author":"Tian","year":"2021"},{"key":"10.1016\/j.ins.2024.121274_br0190","series-title":"Proceedings of Machine Learning and Systems 2020","article-title":"Federated optimization in heterogeneous networks","author":"Tian","year":"2020"},{"key":"10.1016\/j.ins.2024.121274_br0200","series-title":"Proceedings of the 9th International Conference on Learning Representations, ICLR 2021, Austria, May 3-7, 2021, Virtual Event","article-title":"Fedbn: federated learning on non-iid features via local batch normalization","author":"Li","year":"2021"},{"author":"Liang","key":"10.1016\/j.ins.2024.121274_br0210"},{"issue":"1","key":"10.1016\/j.ins.2024.121274_br0220","doi-asserted-by":"crossref","first-page":"904","DOI":"10.1109\/TNET.2023.3299851","article-title":"Accelerating federated learning with data and model parallelism in edge computing","volume":"32","author":"Liao","year":"2024","journal-title":"IEEE\/ACM Trans. Netw."},{"key":"10.1016\/j.ins.2024.121274_br0230","series-title":"Proceedings of the 31st International Joint Conference on Artificial Intelligence","first-page":"2166","article-title":"Adapt to adaptation: learning personalization for cross-silo federated learning","author":"Luo","year":"2022"},{"year":"2019","series-title":"Robust Statistics: Theory and Methods (with R)","author":"Maronna","key":"10.1016\/j.ins.2024.121274_br0240"},{"key":"10.1016\/j.ins.2024.121274_br0250","series-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017"},{"key":"10.1016\/j.ins.2024.121274_br0260","series-title":"Proceedings of the 35th International Conference on Machine Learning","first-page":"3518","article-title":"The hidden vulnerability of distributed learning in byzantium","volume":"vol. 80","author":"Mhamdi","year":"2018"},{"author":"Nguyen","key":"10.1016\/j.ins.2024.121274_br0270"},{"issue":"1","key":"10.1016\/j.ins.2024.121274_br0280","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1109\/TNET.2021.3110052","article-title":"Towards personalized privacy-preserving truth discovery over crowdsourced data streams","volume":"30","author":"Pang","year":"2022","journal-title":"IEEE\/ACM Trans. Netw."},{"key":"10.1016\/j.ins.2024.121274_br0290","series-title":"Proceedings of the 34th Annual Conference on Neural Information Processing Systems 2021","first-page":"840","article-title":"Sageflow: robust federated learning against both stragglers and adversaries","author":"Park","year":"2021"},{"key":"10.1016\/j.ins.2024.121274_br0300","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1016\/j.ins.2022.10.120","article-title":"Byzantine-robust variance-reduced federated learning over distributed non-i.i.d. data","volume":"616","author":"Peng","year":"2022","journal-title":"Inf. Sci."},{"key":"10.1016\/j.ins.2024.121274_br0310","doi-asserted-by":"crossref","first-page":"1142","DOI":"10.1109\/TSP.2022.3153135","article-title":"Robust aggregation for federated learning","volume":"70","author":"Pillutla","year":"2022","journal-title":"IEEE Trans. Signal Process."},{"key":"10.1016\/j.ins.2024.121274_br0320","series-title":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"4743","article-title":"Revisiting personalized federated learning: robustness against backdoor attacks","author":"Qin","year":"2023"},{"key":"10.1016\/j.ins.2024.121274_br0330","series-title":"Proceedings of the 29th Annual Network and Distributed System Security Symposium","article-title":"Deepsight: mitigating backdoor attacks in federated learning through deep model inspection","author":"Rieger","year":"2022"},{"key":"10.1016\/j.ins.2024.121274_br0340","series-title":"Proceedings of the 28th Annual Network and Distributed System Security Symposium","first-page":"1","article-title":"Manipulating the byzantine: optimizing model poisoning attacks and defenses for federated learning","author":"Shejwalkar","year":"2021"},{"key":"10.1016\/j.ins.2024.121274_br0350","series-title":"Proceedings of the 34th Annual Conference on Neural Information Processing Systems 2021","first-page":"12613","article-title":"Enhancing robustness against model poisoning attacks in federated learning from a client perspective","author":"Sun","year":"2021"},{"author":"Sun","key":"10.1016\/j.ins.2024.121274_br0360"},{"year":"2017","series-title":"The EU General Data Protection Regulation (GDPR)","author":"Voigt","key":"10.1016\/j.ins.2024.121274_br0370"},{"key":"10.1016\/j.ins.2024.121274_br0380","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","first-page":"7394","article-title":"A four-pronged defense against byzantine attacks in federated learning","author":"Wan","year":"2023"},{"key":"10.1016\/j.ins.2024.121274_br0390","series-title":"Proceedings of the 33rd Annual Conference on Neural Information Processing Systems 2020","article-title":"Attack of the tails: yes, you really can backdoor federated learning","author":"Wang","year":"2020"},{"issue":"1","key":"10.1016\/j.ins.2024.121274_br0400","doi-asserted-by":"crossref","first-page":"1","DOI":"10.23919\/cje.2022.00.031","article-title":"Attrleaks on the edge: exploiting information leakage from privacy-preserving co-inference","volume":"32","author":"Wang","year":"2023","journal-title":"Chin. J. Electron."},{"key":"10.1016\/j.ins.2024.121274_br0410","series-title":"Proceedings of the 35th Conference on Uncertainty in Artificial Intelligence","first-page":"261","article-title":"Fall of empires: breaking byzantine-tolerant SGD by inner product manipulation","volume":"vol. 115","author":"Xie","year":"2019"},{"issue":"2","key":"10.1016\/j.ins.2024.121274_br0420","doi-asserted-by":"crossref","first-page":"1310","DOI":"10.1109\/TII.2021.3073925","article-title":"Privacy threat and defense for federated learning with non-i.i.d. data in aiot","volume":"18","author":"Xiong","year":"2022","journal-title":"IEEE Trans. Ind. Inform."},{"issue":"9","key":"10.1016\/j.ins.2024.121274_br0430","doi-asserted-by":"crossref","first-page":"16600","DOI":"10.1109\/TITS.2022.3149657","article-title":"Efficient citycam-to-edge cooperative learning for vehicle counting in ITS","volume":"23","author":"Xu","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"Part","key":"10.1016\/j.ins.2024.121274_br0440","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.tcs.2022.09.023","article-title":"Analysis on methods to effectively improve transfer learning performance","volume":"940","author":"Xu","year":"2023","journal-title":"Theor. Comput. Sci."},{"key":"10.1016\/j.ins.2024.121274_br0450","series-title":"Proceedings of the 42nd IEEE International Conference on Distributed Computing Systems","first-page":"1223","article-title":"Byzantine-robust federated learning through collaborative malicious gradient filtering","author":"Xu","year":"2022"},{"key":"10.1016\/j.ins.2024.121274_br0460","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2023.119743","article-title":"Efficient and persistent backdoor attack by boundary trigger set constructing against federated learning","volume":"651","author":"Yang","year":"2023","journal-title":"Inf. Sci."},{"key":"10.1016\/j.ins.2024.121274_br0470","series-title":"Proceedings of the 35th International Conference on Machine Learning","first-page":"5636","article-title":"Byzantine-robust distributed learning: towards optimal statistical rates","volume":"vol. 80","author":"Yin","year":"2018"},{"key":"10.1016\/j.ins.2024.121274_br0480","series-title":"Proceedings of the 37th AAAI Conference on Artificial Intelligence","first-page":"11237","article-title":"Fedala: adaptive local aggregation for personalized federated learning","author":"Zhang","year":"2023"},{"key":"10.1016\/j.ins.2024.121274_br0490","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2023.119873","article-title":"Fedsw: federated learning with adaptive sample weights","volume":"654","author":"Zhao","year":"2024","journal-title":"Inf. Sci."}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025524011885?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025524011885?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T08:32:39Z","timestamp":1725265959000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0020025524011885"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":49,"alternative-id":["S0020025524011885"],"URL":"https:\/\/doi.org\/10.1016\/j.ins.2024.121274","relation":{},"ISSN":["0020-0255"],"issn-type":[{"type":"print","value":"0020-0255"}],"subject":[],"published":{"date-parts":[[2024,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"FedNor: A robust training framework for federated learning based on normal aggregation","name":"articletitle","label":"Article Title"},{"value":"Information Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ins.2024.121274","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"121274"}}