{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T05:58:42Z","timestamp":1780725522641,"version":"3.54.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Institute of Information & Communications Technology Planning & Evaluation (IITP) Grant"},{"name":"Korean Government","award":["20210007270012002"],"award-info":[{"award-number":["20210007270012002"]}]},{"name":"Research Grant funded by Seoul Women\u2019s University","award":["2020-0454"],"award-info":[{"award-number":["2020-0454"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3124020","type":"journal-article","created":{"date-parts":[[2021,10,28]],"date-time":"2021-10-28T19:30:16Z","timestamp":1635449416000},"page":"148090-148103","source":"Crossref","is-referenced-by-count":16,"title":["Enhancing Differential Privacy for Federated Learning at Scale"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3169-1356","authenticated-orcid":false,"given":"Chunghun","family":"Baek","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4789-3347","authenticated-orcid":false,"given":"Sungwook","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongkyun","family":"Nam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jihoon","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2013.30"},{"key":"ref38","first-page":"1","article-title":"Differentially private meta-learning","author":"li","year":"2020","journal-title":"Proc ICLR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.2988575"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3064047"},{"key":"ref31","article-title":"Scalable private learning with PATE","author":"papernot","year":"2018","journal-title":"Proc ICLR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00019"},{"key":"ref37","article-title":"Protection against reconstruction and its applications in private federated learning","author":"bhowmick","year":"2018","journal-title":"arXiv 1812 00984"},{"key":"ref36","article-title":"Gaussian differential privacy","author":"dong","year":"2019","journal-title":"arXiv 1905 02383"},{"key":"ref35","first-page":"2251","article-title":"Federated f-differential privacy","volume":"130","author":"zheng","year":"2021","journal-title":"Proc AISTATS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-020-00780-4"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00001"},{"key":"ref27","first-page":"1069","article-title":"Differentially private empirical risk minimization","volume":"12","author":"chaudhuri","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref2","year":"2021","journal-title":"Federated learning Collaborative machine learning without centralized training data"},{"key":"ref1","article-title":"Towards federated learning at scale: System design","author":"bonawitz","year":"2019","journal-title":"Proc MLSys"},{"key":"ref20","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"2017","journal-title":"Proc AISTATS"},{"key":"ref22","year":"0","journal-title":"FEMNIST Dataset"},{"key":"ref21","year":"0","journal-title":"MNIST Handwritten Digit Database"},{"key":"ref24","first-page":"265","article-title":"Calibrating noise to sensitivity in private data analysis","author":"dwork","year":"2006","journal-title":"Proc TCC"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/11787006_1"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2014.56"},{"key":"ref25","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":"ref50","year":"2021","journal-title":"Libraries for FEMNIST"},{"key":"ref51","article-title":"Federated learning with non-iid data","author":"zhao","year":"2018","journal-title":"arXiv 1806 00582"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/359168.359176"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1976.1055638"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3338501.3357370"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.18"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3338501.3357371"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-96884-1_20"},{"key":"ref13","first-page":"1310","article-title":"Privacy-preserving deep learning","author":"shokri","year":"2015","journal-title":"Proc 53rd Annu Allerton Conf Commun Control Comput (Allerton)"},{"key":"ref14","article-title":"Differentially private federated learning: A client level perspective","author":"geyer","year":"2017","journal-title":"arXiv 1712 07557"},{"key":"ref15","first-page":"7575","article-title":"cpSGD: Communication-efficient and differentially-private distributed SGD","author":"agarwal","year":"2018","journal-title":"Proc NIPS"},{"key":"ref16","article-title":"Differentially private learning with adaptive clipping","author":"thakkar","year":"2019","journal-title":"arXiv 1905 03871"},{"key":"ref17","article-title":"Learning differentially private recurrent language models","author":"mcmahan","year":"2018","journal-title":"Proc ICLR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412771"},{"key":"ref19","article-title":"D2P-Fed: Differentially private federated learning with efficient communication","author":"wang","year":"2020","journal-title":"arXiv 2006 13039"},{"key":"ref4","article-title":"Build trust through better privacy","author":"prakash","year":"2020","journal-title":"Proc WWDC 2020"},{"key":"ref3","year":"2021","journal-title":"Privacy That Works for Everyone"},{"key":"ref6","first-page":"267","article-title":"The secret sharer: Evaluating and testing unintended memorization in neural networks","author":"carlini","year":"2019","journal-title":"Proc Usenix Secur Symp"},{"key":"ref5","article-title":"Designing for privacy","author":"xue","year":"2019","journal-title":"Proc WWDC 2019"},{"key":"ref8","article-title":"Understanding deep learning requires rethinking generalization","author":"zhang","year":"2017","journal-title":"Proc ICLR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"ref49","year":"0","journal-title":"RDP Accountant in Tensorflow-Privacy"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133982"},{"key":"ref46","first-page":"1","article-title":"Semi-supervised knowledge transfer for deep learning from private training data","author":"papernot","year":"2017","journal-title":"Proc ICLR"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"188","DOI":"10.2478\/popets-2021-0011","article-title":"FALCON: Honest-majority maliciously secure framework for private deep learning","author":"wagh","year":"2021","journal-title":"Proc Priv Enhancing Technol (PoPETs)"},{"key":"ref48","year":"0","journal-title":"Tutorial for MNIST in Tensorflow"},{"key":"ref47","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref42","article-title":"Secure computation for machine learning with SPDZ","author":"chen","year":"2019","journal-title":"arXiv 1901 00329"},{"key":"ref41","first-page":"812","article-title":"Low latency privacy preserving inference","volume":"97","author":"brutzkus","year":"2019","journal-title":"Proc ICML"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3196494.3196522"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3243734.3243760"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09592806.pdf?arnumber=9592806","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,14]],"date-time":"2022-03-14T21:44:43Z","timestamp":1647294283000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9592806\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3124020","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}