{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T07:21:35Z","timestamp":1763018495780,"version":"3.28.0"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1109\/globecom46510.2021.9685232","type":"proceedings-article","created":{"date-parts":[[2022,2,2]],"date-time":"2022-02-02T21:59:04Z","timestamp":1643839144000},"page":"01-06","source":"Crossref","is-referenced-by-count":6,"title":["AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learning"],"prefix":"10.1109","author":[{"given":"Yusuke","family":"Koda","sequence":"first","affiliation":[{"name":"University of Oulu,Centre for Wireless Communications,Oulu,Finland,90014"}]},{"given":"Jihong","family":"Park","sequence":"additional","affiliation":[{"name":"Deakin University,School of Information Technology,Geelong,Australia,VIC 3220"}]},{"given":"Mehdi","family":"Bennis","sequence":"additional","affiliation":[{"name":"University of Oulu,Centre for Wireless Communications,Oulu,Finland,90014"}]},{"given":"Praneeth","family":"Vepakomma","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Cambridge,MA,USA,02139"}]},{"given":"Ramesh","family":"Raskar","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Cambridge,MA,USA,02139"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"2017","journal-title":"Proc AISTATS 2017"},{"key":"ref11","article-title":"Advances and open problems in federated learning","volume":"14","author":"mcmahan","year":"2021","journal-title":"Foundations & Trends in Mach Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2961673"},{"key":"ref13","article-title":"Over-the-air federated learning from heterogeneous data","author":"sery","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref14","first-page":"263","article-title":"Rényi differential privacy","author":"mironov","year":"2017","journal-title":"Proc IEEE CSF 2017"},{"journal-title":"Iris Dataset","year":"0","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref17","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"2013","journal-title":"Proc ICML 2013"},{"key":"ref4","article-title":"Harnessing wireless channels for scalable and privacy-preserving federated learning","author":"elgabli","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3036948"},{"key":"ref6","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813677"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2019.8849381"},{"key":"ref7","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322199"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2946245"},{"key":"ref9","article-title":"DP-instahide: Provably defusing poisoning and backdoor attacks with differentially private data augmentations","author":"borgnia","year":"2021","journal-title":"ArXiv Preprint"}],"event":{"name":"GLOBECOM 2021 - 2021 IEEE Global Communications Conference","start":{"date-parts":[[2021,12,7]]},"location":"Madrid, Spain","end":{"date-parts":[[2021,12,11]]}},"container-title":["2021 IEEE Global Communications Conference (GLOBECOM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9685019\/9685006\/09685232.pdf?arnumber=9685232","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:46:53Z","timestamp":1659484013000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9685232\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/globecom46510.2021.9685232","relation":{},"subject":[],"published":{"date-parts":[[2021,12]]}}}