{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T16:48:48Z","timestamp":1774716528621,"version":"3.50.1"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"OUSD (R&E)\/RT&L under Cooperative Agreement","award":["W911NF-20-2-0267"],"award-info":[{"award-number":["W911NF-20-2-0267"]}]},{"name":"NSF CAREER","award":["CCF-2144927"],"award-info":[{"award-number":["CCF-2144927"]}]},{"name":"UCR OASIS Fellowship"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Commun."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tcomm.2024.3403475","type":"journal-article","created":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T17:24:03Z","timestamp":1716225843000},"page":"6883-6899","source":"Crossref","is-referenced-by-count":5,"title":["Secure Gradient Aggregation With Sparsification for Resource-Limited Federated Learning"],"prefix":"10.1109","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2607-1927","authenticated-orcid":false,"given":"Hasin","family":"Us Sami","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of California at Riverside, Riverside, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3246-1667","authenticated-orcid":false,"given":"Ba\u015fak","family":"G\u00fcler","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of California at Riverside, Riverside, CA, USA"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist. (AISTATS)","author":"McMahan"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63076-8_2"},{"key":"ref3","article-title":"IDLG: Improved deep leakage from gradients","author":"Zhao","year":"2020","journal-title":"arXiv:2001.02610"},{"key":"ref4","first-page":"1","article-title":"Inverting gradients\u2014How easy is it to break privacy in federated learning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Geiping"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01607"},{"key":"ref6","first-page":"1","article-title":"Fishing for user data in large-batch federated learning via gradient magnification","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Wen"},{"key":"ref7","first-page":"1","article-title":"Robbing the fed: Directly obtaining private data in federated learning with modified models","volume-title":"Proc. 10th Int. Conf. Learn. Represent. (ICLR)","author":"Fowl"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133982"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417885"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SP46215.2023.10179434"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3266919"},{"key":"ref12","first-page":"1","article-title":"Sparsified SGD with memory","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Stich"},{"key":"ref13","first-page":"1","article-title":"The convergence of sparsified gradient methods","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Alistarh"},{"key":"ref14","first-page":"2530","article-title":"A linear speedup analysis of distributed deep learning with sparse and quantized communication","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jiang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00060"},{"key":"ref16","first-page":"1","article-title":"Detached error feedback for distributed SGD with random sparsification","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Xu"},{"key":"ref17","article-title":"Federated learning with sparsified model perturbation: Improving accuracy under client-level differential privacy","author":"Hu","year":"2022","journal-title":"arXiv:2202.07178"},{"key":"ref18","first-page":"36058","article-title":"CocktailSGD: Fine-tuning foundation models over 500Mbps networks","volume-title":"Proc. 40th Int. Conf. Mach. Learn. (ICML)","author":"Wang"},{"key":"ref19","first-page":"1","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","volume-title":"Proc. 6th Int. Conf. Learn. Represent. (ICLR)","author":"Lin"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17254"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3192050"},{"key":"ref22","first-page":"1","article-title":"Rethinking gradient sparsification as total error minimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sahu"},{"key":"ref23","first-page":"1","article-title":"Gradient disaggregation: Breaking privacy in federated learning by reconstructing the user participant matrix","volume-title":"Proc. 38th Int. Conf. Mach. Learn. (ICML)","author":"Lam"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3548606.3560557"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3227761"},{"key":"ref26","first-page":"1","article-title":"LightSecAGG: A lightweight and versatile design for secure aggregation in federated learning","volume-title":"Proc. Mach. Learn. Syst.","author":"So"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26177"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM48099.2022.10001481"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2022.102993"},{"key":"ref30","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":"ref31","first-page":"1","article-title":"The Poisson binomial mechanism for unbiased federated learning with secure aggregation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref32","first-page":"1379","article-title":"Efficient differentially private secure aggregation for federated learning via hardness of learning with errors","volume-title":"Proc. 31st USENIX Secur. Symp. (USENIX Secur.)","author":"Stevens"},{"key":"ref33","first-page":"1","article-title":"Prio: Private, robust, and scalable computation of aggregate statistics","volume-title":"Proc. Symp. Netw. Syst. Design Implement.","author":"Corrigan-Gibbs"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3041404"},{"key":"ref35","first-page":"7587","article-title":"SparseFed: Mitigating model poisoning attacks in federated learning with sparsification","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Panda"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3548606.3560611"},{"key":"ref37","volume-title":"ACORN: Input validation for secure aggregation","author":"Bell"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3212174"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3488932.3517395"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20903"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/SP46215.2023.10179400"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/SP46215.2023.10179468"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3295949"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3579856.3595805"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.3042094"},{"key":"ref46","first-page":"1","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Alistarh"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2023.3292187"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2023.3339450"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2022.3165400"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1137\/08073408x"},{"key":"ref53","article-title":"LEAF: A benchmark for federated settings","author":"Caldas","year":"2018","journal-title":"arXiv:1812.01097"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.56553\/popets-2023-0030"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1976.1055638"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/359168.359176"},{"key":"ref57","first-page":"1","article-title":"Lagrange coded computing: Optimal design for resiliency, security, and privacy","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","author":"Yu"}],"container-title":["IEEE Transactions on Communications"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/26\/10756213\/10535199-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/26\/10756213\/10535199.pdf?arnumber=10535199","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:20:29Z","timestamp":1732666829000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10535199\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":57,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcomm.2024.3403475","relation":{},"ISSN":["0090-6778","1558-0857"],"issn-type":[{"value":"0090-6778","type":"print"},{"value":"1558-0857","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}