{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T15:35:51Z","timestamp":1771515351063,"version":"3.50.1"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tmc.2025.3564390","type":"journal-article","created":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T13:35:24Z","timestamp":1745847324000},"page":"9934-9950","source":"Crossref","is-referenced-by-count":3,"title":["Compressed Private Aggregation for Scalable and Robust Federated Learning Over Massive Networks"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0266-7792","authenticated-orcid":false,"given":"Natalie","family":"Lang","sequence":"first","affiliation":[{"name":"School of ECE, Ben-Gurion University of the Negev, Be’er-Sheva, Israel"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2234-929X","authenticated-orcid":false,"given":"Nir","family":"Shlezinger","sequence":"additional","affiliation":[{"name":"School of ECE, Ben-Gurion University of the Negev, Be’er-Sheva, Israel"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5053-5909","authenticated-orcid":false,"given":"Rafael G. L.","family":"D\u2019Oliveira","sequence":"additional","affiliation":[{"name":"School of Mathematical and Statistical Sciences, Clemson University, Clemson, SC, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4515-2213","authenticated-orcid":false,"given":"Salim El","family":"Rouayheb","sequence":"additional","affiliation":[{"name":"Department of ECE, Rutgers University, Piscataway, NJ, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096363"},{"key":"ref2","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3125282"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2921977"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63076-8_2"},{"key":"ref8","article-title":"iDLG: Improved deep leakage from gradients","author":"Zhao","year":"2020"},{"key":"ref9","first-page":"7232","article-title":"Evaluating gradient inversion attacks and defenses in federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01607"},{"key":"ref11","first-page":"1605","article-title":"Local model poisoning attacks to byzantine-robust federated learning","volume-title":"Proc. USENIX Secur. Symp.","author":"Fang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.10.007"},{"key":"ref13","first-page":"5132","article-title":"Scaffold: Stochastic controlled averaging for federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Karimireddy"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2024789118"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413764"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.2988575"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/217"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59410-7_33"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3460427"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-0186-1"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2262116"},{"key":"ref22","first-page":"5650","article-title":"Byzantine-robust distributed learning: Towards optimal statistical rates","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yin"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011544"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS47774.2020.00026"},{"key":"ref25","article-title":"Federated learning: Strategies for improving communication efficiency","author":"Kone\u010dn\u00fd","year":"2016"},{"key":"ref26","article-title":"Distributed deep learning on edge-devices in the parameter server model","volume-title":"Proc. Workshop Decentralized Mach. Learn., Optim. Privacy","author":"Hardy"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1045"},{"key":"ref28","first-page":"5977","article-title":"The convergence of sparsified gradient methods","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alistarh"},{"key":"ref29","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin"},{"key":"ref30","first-page":"1709","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alistarh"},{"key":"ref31","first-page":"2021","article-title":"FedPAQ: A communication-efficient federated learning method with periodic averaging and quantization","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Reisizadeh"},{"key":"ref32","first-page":"560","article-title":"signSGD: Compressed optimisation for non-convex problems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bernstein"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.3046971"},{"key":"ref34","first-page":"129","article-title":"Natural compression for distributed deep learning","volume-title":"Proc. 3rd Annu. Conf. Math. Sci. Mach. Learn.","author":"Horv\u00f3th"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761315"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9414538"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC51304.2022.9833991"},{"key":"ref38","first-page":"2","article-title":"Compressive differentially private federated learning through universal vector quantization","volume-title":"Proc. AAAI Workshop Privacy-Preserving Artif. Intell.","author":"Amiri"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3244092"},{"key":"ref40","first-page":"296","article-title":"Privacy-aware compression for federated data analysis","volume-title":"Proc. Conf. Uncertainty Artif. Intell.","author":"Chaudhuri"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3142357"},{"key":"ref42","first-page":"1","article-title":"Cabdriver: Concentration to accurate boundaries while distorting randomly input variables to elude recognition","volume-title":"Proc. Int. ITG Workshop Smart Antennas","author":"Thesmar"},{"key":"ref43","article-title":"Nested dithered quantization for communication reduction in distributed training","author":"Abdi","year":"2019"},{"key":"ref44","article-title":"Local SGD converges fast and communicates little","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Stich"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/18.720541"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/18.119699"},{"issue":"5","key":"ref47","first-page":"355","article-title":"Quantization and dither: A theoretical survey","volume":"40","author":"Lipshitz","year":"1992","journal-title":"J. Audio Eng. Soc."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/18.256489"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/18.508838"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2002.1003821"},{"key":"ref51","article-title":"Lecture notes on information theory","author":"Polyanskiy","year":"2012\u20132017"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2017.2715334"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3226070"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1137\/090756090"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6096"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3037194"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/8829523"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3390\/s20247030"},{"key":"ref59","first-page":"10185","article-title":"Elliptical perturbations for differential privacy","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Reimherr"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.2307\/2283137"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1142\/S0218488502001648"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00390-3"},{"key":"ref63","first-page":"16937","article-title":"Inverting gradients-how easy is it to break privacy in federated learning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Geiping"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2010.12"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-6568-7"},{"key":"ref66","article-title":"signSGD with majority vote is communication efficient and fault tolerant","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bernstein"},{"key":"ref67","first-page":"5201","article-title":"The distributed discrete gaussian mechanism for federated learning with secure aggregation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kairouz"},{"key":"ref68","first-page":"5052","article-title":"The skellam mechanism for differentially private federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Agarwal"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1561\/9781601988195"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2935864"},{"key":"ref71","article-title":"On the convergence of FedAvg on non-IID data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/tcomm.2024.3486979"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.29012\/jpc.v7i3.405"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1996.8.3.643"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3090323"},{"key":"ref77","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11154819\/10979227.pdf?arnumber=10979227","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T19:53:04Z","timestamp":1757533984000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10979227\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":77,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2025.3564390","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}