{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:07:41Z","timestamp":1775912861314,"version":"3.50.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["NSF 2038029"],"award-info":[{"award-number":["NSF 2038029"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["NSF 1564097"],"award-info":[{"award-number":["NSF 1564097"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CISCO"},{"name":"IBM"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1109\/tpds.2023.3273490","type":"journal-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:40:22Z","timestamp":1683308422000},"page":"2040-2054","source":"Crossref","is-referenced-by-count":29,"title":["Securing Distributed SGD Against Gradient Leakage Threats"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9177-114X","authenticated-orcid":false,"given":"Wenqi","family":"Wei","sequence":"first","affiliation":[{"name":"Computer and Information Science Department, Fordham University, New York City, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4138-3082","authenticated-orcid":false,"given":"Ling","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Georgia Institute of Technology, Atlanta, GA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0721-7424","authenticated-orcid":false,"given":"Jingya","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, Jiangsu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5917-2577","authenticated-orcid":false,"given":"Ka-Ho","family":"Chow","sequence":"additional","affiliation":[{"name":"School of Computer Science, Georgia Institute of Technology, Atlanta, GA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8761-5486","authenticated-orcid":false,"given":"Yanzhao","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Georgia Institute of Technology, Atlanta, GA, USA"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Learning differentially private recurrent language models","author":"mcmahan","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref35","first-page":"739","article-title":"Comprehensive privacy analysis of deep learning: Stand-alone and federated learning under passive and active white-box inference attacks","author":"nasr","year":"2019","journal-title":"Proc IEEE Symp Secur Privacy"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3139777"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00081"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00029"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.2988575"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2019.2897554"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737416"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"1333","DOI":"10.1109\/TIFS.2017.2787987","article-title":"Privacy-preserving deep learning via additively homomorphic encryption","volume":"13","author":"aono","year":"2018","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/11681878_14"},{"key":"ref33","first-page":"7232","article-title":"Evaluating gradient inversion attacks and defenses in federated learning","author":"huang","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref10","article-title":"Scalable private learning with PATE","author":"papernot","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref32","article-title":"R-GAP: Recursive gradient attack on privacy","author":"zhu","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref2","first-page":"14 747","article-title":"Deep leakage from gradients","author":"zhu","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref1","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"2017","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref17","first-page":"6277","article-title":"Privacy amplification by subsampling: Tight analyses via couplings and divergences","author":"balle","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref39","first-page":"1345","article-title":"High accuracy and high fidelity extraction of neural networks","author":"jagielski","year":"2020","journal-title":"Proc USENIX Conf Secur Symp"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1559845.1559850"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813677"},{"key":"ref19","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","author":"lin","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref18","article-title":"Federated learning: Strategies for improving communication efficiency","author":"kone?n?","year":"2016"},{"key":"ref24","first-page":"1069","article-title":"Differentially private empirical risk minimization","volume":"12","author":"chaudhuri","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48910-X_16"},{"key":"ref23","article-title":"Snapshot ensembles: Train 1, get M for free","author":"huang","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/217"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2010.12"},{"key":"ref25","volume":"317","author":"rockafellar","year":"2009","journal-title":"Variational Analysis"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3458864.3466628"},{"key":"ref20","first-page":"1310","article-title":"Privacy-preserving deep learning","author":"shokri","year":"2015","journal-title":"Proc ACM SIGSAC Conf Comput Commun Secur"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1137\/090756090"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133982"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9006104"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3378679.3394533"},{"key":"ref21","article-title":"Differentially private federated learning: A client level perspective","author":"geyer","year":"2017"},{"key":"ref43","first-page":"2365","article-title":"Secure and utility-aware data collection with condensed local differential privacy","volume":"18","author":"gursoy","year":"2021","journal-title":"IEEE Trans Dependable Secure Comput"},{"key":"ref28","article-title":"AdaCliP: Adaptive clipping for private SGD","author":"pichapati","year":"2019"},{"key":"ref27","article-title":"Differentially private learning with adaptive clipping","author":"thakkar","year":"2019"},{"key":"ref29","first-page":"263","article-title":"Rényi differential privacy","author":"mironov","year":"2017","journal-title":"Proc 30th IEEE Symp Foundations of Computer Science"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"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":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00019"},{"key":"ref4","first-page":"16 937","article-title":"Inverting gradients - how easy is it to break privacy in federated learning?","author":"geiping","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref3","article-title":"iDLG: Improved deep leakage from gradients","author":"zhao","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01607"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58951-6_27"},{"key":"ref40","first-page":"7575","article-title":"CPSGD: Communication-efficient and differentially-private distributed SGD","author":"agarwal","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/71\/10132303\/10119168-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/10132303\/10119168.pdf?arnumber=10119168","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,6]],"date-time":"2023-07-06T23:15:05Z","timestamp":1688685305000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10119168\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":47,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2023.3273490","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7]]}}}