{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T18:56:20Z","timestamp":1793904980011,"version":"4.8.0"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2139304"],"award-info":[{"award-number":["2139304"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2007714"],"award-info":[{"award-number":["2007714"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Areas Inf. Theory"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/jsait.2024.3366225","type":"journal-article","created":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T19:03:29Z","timestamp":1708023809000},"page":"12-27","source":"Crossref","is-referenced-by-count":10,"title":["Multi-Message Shuffled Privacy in Federated Learning"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9828-6534","authenticated-orcid":false,"given":"Antonious M.","family":"Girgis","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering (ECE), University of California at Los Angeles, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7313-9861","authenticated-orcid":false,"given":"Suhas","family":"Diggavi","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering (ECE), University of California at Los Angeles, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Distributed mean estimation for multi-message\n                        shuffled privacy","volume-title":"Proc. Fed. Learn. Anal.\n                        Pract., Algorithms, Syst., Appl., Oppor., ICML Workshops","author":"Girgis"},{"key":"ref2","first-page":"1273","article-title":"Communication-efficient learning of deep networks\n                        from decentralized data","volume-title":"Proc. Artif.\n                        Intell. Statist.","author":"McMahan"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref4","first-page":"1","article-title":"Communication efficient distributed machine learning\n                        with the parameter server","volume-title":"Proc. Adv.\n                        Neural Inf. Process. Syst.","volume":"27","author":"Li"},{"key":"ref5","first-page":"560","article-title":"signSGD: Compressed optimisation for non-convex\n                        problems","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Bernstein"},{"key":"ref6","first-page":"1","article-title":"QSGD: Communication-efficient SGD via gradient\n                        quantization and encoding","volume-title":"Proc. Adv.\n                        Neural Inf. Process. Syst.","volume":"30","author":"Alistarh"},{"key":"ref7","first-page":"1","article-title":"Sparsified SGD with memory","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Stich"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2022.3161620"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63076-8_2"},{"key":"ref10","first-page":"16937","article-title":"Inverting gradients\u2013How easy is it to break\n                        privacy in federated learning?","volume-title":"Proc.\n                        Adv. Neural Inf. Process. Syst.","volume":"33","author":"Geiping"},{"key":"ref11","first-page":"2633","article-title":"Extracting training data from large language\n                        models","volume-title":"Proc. 30th USENIX Secur.\n                        Symp.","author":"Carlini"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/11681878_14"},{"issue":"3","key":"ref14","first-page":"1","article-title":"Differentially private empirical risk\n                        minimization","volume":"12","author":"Chaudhuri","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2014.56"},{"key":"ref16","first-page":"5213","article-title":"Practical and private (deep) learning without\n                        sampling or shuffling","volume-title":"Proc. Int. Conf.\n                        Mach. Learn.","author":"Kairouz"},{"key":"ref17","first-page":"2521","article-title":"Shuffled model of differential privacy in federated\n                        learning","volume-title":"Proc. Int. Conf. Artif. Intell.\n                        Statist. (AISTATS)","author":"Girgis"},{"key":"ref18","first-page":"5201","article-title":"The distributed discrete Gaussian mechanism for\n                        federated learning with secure aggregation","volume-title":"Proc. Int. Conf. Mach. Learn., ICML","volume":"139","author":"Kairouz"},{"key":"ref19","first-page":"3329","article-title":"Distributed mean estimation with limited\n                        communication","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Suresh"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref21","first-page":"296","article-title":"Privacy-aware compression for federated data\n                        analysis","volume-title":"Proc. 38th Conf. Uncertain.\n                        Artif. Intell.","author":"Chaudhuri"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1137\/090756090"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2013.53"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132769"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611975482.151"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-17653-2_13"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT45174.2021.9517906"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77883-5_16"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417242"},{"key":"ref30","first-page":"1","article-title":"Shuffle private stochastic convex\n                        optimization","volume-title":"Proc. Int. Conf. Learn.\n                        Represent. (ICLR)","author":"Cheu"},{"key":"ref31","first-page":"1441","article-title":"Locally private k-means in one\n                    round","volume-title":"Proc. Int. Conf. Mach.\n                    Learn.","author":"Chang"},{"key":"ref32","first-page":"3056","article-title":"The fundamental price of secure aggregation in\n                        differentially private federated learning","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref33","article-title":"Privacy amplification via compression: Achieving the\n                        optimal privacy-accuracy-communication trade-off in distributed mean\n                        estimation","author":"Chen","year":"2023","journal-title":"arXiv:2304.01541"},{"key":"ref34","first-page":"3312","article-title":"Breaking the communication-privacy-accuracy\n                        trilemma","volume-title":"Proc. Adv. Neural Inf. Process.\n                        Syst.","volume":"33","author":"Chen"},{"key":"ref35","first-page":"1046","article-title":"Optimal algorithms for mean estimation under local\n                        differential privacy","volume-title":"Proc. Int. Conf.\n                        Mach. Learn.","author":"Asi"},{"key":"ref36","article-title":"The interpolated MVU mechanism for\n                        communication-efficient private federated learning","author":"Guo","year":"2022","journal-title":"arXiv:2211.03942"},{"key":"ref37","first-page":"3505","article-title":"Private counting from anonymous messages:\n                        Near-optimal accuracy with vanishing communication\n                    overhead","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Ghazi"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2006.25"},{"key":"ref39","article-title":"Multi-message shuffled privacy in federated\n                        learning","author":"Girgis","year":"2023","journal-title":"arXiv:2302.11152"},{"key":"ref40","first-page":"7564","article-title":"cpSGD: Communication-efficient and\n                        differentially-private distributed SGD","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Agarwal"},{"key":"ref41","article-title":"Encode, shuffle, analyze privacy revisited:\n                        Formalizations and empirical evaluation","author":"Erlingsson","year":"2020","journal-title":"arXiv:2001.03618"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2021.3056102"},{"key":"ref43","first-page":"29181","article-title":"Renyi differential privacy of the subsampled shuffle\n                        model in distributed learning","volume-title":"Proc. Adv.\n                        Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Girgis"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3460120.3484794"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611977554.ch181"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1561\/9781601988195"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CSF.2017.11"},{"key":"ref48","first-page":"1","article-title":"The discrete Gaussian for differential\n                        privacy","volume-title":"Proc. Adv. Neural Inf. Process.\n                        Syst.","author":"Canonne"},{"key":"ref49","first-page":"2496","article-title":"Hypothesis testing interpretations and Renyi\n                        differential privacy","volume-title":"Proc. Int. Conf.\n                        Artif. Intell. Statist. (AISTATS)","author":"Balle"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.2307\/2283137"},{"key":"ref51","first-page":"3692","article-title":"Differentially private aggregation in the shuffle\n                        model: Almost central accuracy in almost a single\n                    message","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Ghazi"},{"key":"ref52","first-page":"1","article-title":"Pure differentially private summation from anonymous\n                        messages","volume-title":"Proc. 1st Conf. Inf.-Theor.\n                        Cryptogr.","author":"Ghazi"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1070\/IM1977v011n02ABEH001719"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2048458"},{"key":"ref55","article-title":"Expanding the reach of federated learning by reducing\n                        client resource requirements","author":"Caldas","year":"2018","journal-title":"arXiv:1812.07210"},{"key":"ref56","first-page":"3208","article-title":"Lossless compression of efficient private local\n                        randomizers","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Feldman"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/2591796.2591877"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.29012\/jpc.723"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS52979.2021.00096"},{"key":"ref60","article-title":"Protection against reconstruction and its\n                        applications in private federated learning","author":"Bhowmick","year":"2018","journal-title":"arXiv:1812.00984"},{"key":"ref61","first-page":"12466","article-title":"Learning with user-level\n                    privacy","volume-title":"Proc. Adv. Neural Inf. Process.\n                        Syst.","volume":"34","author":"Levy"}],"container-title":["IEEE Journal on Selected Areas in Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/8700143\/10461668\/10436711-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8700143\/10461668\/10436711.pdf?arnumber=10436711","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T21:05:06Z","timestamp":1736543106000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10436711\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/jsait.2024.3366225","relation":{},"ISSN":["2641-8770"],"issn-type":[{"value":"2641-8770","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}