{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:48:06Z","timestamp":1777128486553,"version":"3.51.4"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,3]],"date-time":"2022-10-03T00:00:00Z","timestamp":1664755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,3]],"date-time":"2022-10-03T00:00:00Z","timestamp":1664755200000},"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":[[2022,10,3]]},"DOI":"10.1109\/cns56114.2022.9947266","type":"proceedings-article","created":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T20:49:54Z","timestamp":1668804594000},"page":"127-135","source":"Crossref","is-referenced-by-count":7,"title":["Agent-Level Differentially Private Federated Learning via Compressed Model Perturbation"],"prefix":"10.1109","author":[{"given":"Yuanxiong","family":"Guo","sequence":"first","affiliation":[{"name":"University of Texas at San Antonio,Department of Information Systems and Cyber Security,San Antonio,TX,78249"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Nevada,Department of Computer Science and Engineering,Reno, Reno,NV,89557"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanmin","family":"Gong","sequence":"additional","affiliation":[{"name":"University of Texas at San Antonio,Department of Electrical and Computer Engineering,San Antonio,TX,78249"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322475"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2016.2515610"},{"key":"ref33","first-page":"12673","article-title":"GS-WGAN: A gradient-sanitized approach for learning differentially private generators","volume":"33","author":"chen","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref32","article-title":"Differentially private learning needs better features (or much more data)","author":"tramer","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"9312","DOI":"10.1609\/aaai.v35i10.17123","article-title":"Tem-pered sigmoid activations for deep learning with differential privacy","volume":"35","author":"papernot","year":"2021","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref30","author":"xiao","year":"2017","journal-title":"Fashion-mnist a novel image dataset for benchmarking machine learning algorithms"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CNS.2018.8433181"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2931068"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2991416"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133982"},{"key":"ref40","article-title":"Bypassing the ambient dimension: Private SGD with gradient subspace identification","author":"zhou","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417885"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/OJCS.2021.3099108"},{"key":"ref13","first-page":"1299","article-title":"Gradient sparsification for communication-efficient distributed optimization","author":"wangni","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Privacy for free: Communication-efficient learning with differential privacy using sketches","author":"li","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref15","article-title":"cpSGD: Communication-efficient and differentially-private distributed SGD","author":"agarwal","year":"2018","journal-title":"Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16887"},{"key":"ref17","first-page":"254","article-title":"Stronger generalization bounds for deep nets via a compression approach","author":"arora","year":"2018","journal-title":"Int Conference on Machine Learning"},{"key":"ref18","first-page":"1","article-title":"Implicit self-regularization in deep neural networks: Evidence from random matrix theory and implications for learning","volume":"22","author":"martin","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CSF.2017.11"},{"key":"ref28","article-title":"Opacus: User-friendly differential privacy library in PyTorch","author":"yousefpour","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"ref27","article-title":"Communication efficient federated learning with secure aggregation and differential privacy","author":"chen","year":"2021","journal-title":"NeurIPS 2021 Workshop Privacy in Machine Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813677"},{"key":"ref6","article-title":"Atomo: Communication-efficient learning via atomic sparsification","volume":"31","author":"wang","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/202"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1561\/0400000042"},{"key":"ref8","first-page":"1709","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","author":"alistarh","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref7","first-page":"560","article-title":"signSGD: Compressed optimisation for non-convex problems","author":"bernstein","year":"2018","journal-title":"Inter-national Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref9","article-title":"PowerSGD: Practical low-rank gradient compression for distributed optimization","volume":"32","author":"vogels","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref1","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"2017","journal-title":"Artificial Intelligence and Statistics"},{"key":"ref20","first-page":"1226","article-title":"Subsampled r&#x00E9;nyi differential privacy and analytical moments accountant","author":"wang","year":"2019","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref22","article-title":"Learning differ-entially private recurrent language models","author":"mcmahan","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref21","article-title":"Efficient privacy-preserving nonconvex optimization","author":"wang","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref42","article-title":"Hybrid local SGD for federated learning with heterogeneous communications","author":"guo","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3338501.3357370"},{"key":"ref41","article-title":"Do not let privacy overbill utility: Gradient embedding perturbation for private learning","author":"yu","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2457317.2457343"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF44664.2019.9049066"},{"key":"ref25","first-page":"121","article-title":"Computational differential privacy from lattice-based cryptography","author":"valovich","year":"2017","journal-title":"International Conference on Number-Theoretic Methods in Cryptology"}],"event":{"name":"2022 IEEE Conference on Communications and Network Security (CNS)","location":"Austin, TX, USA","start":{"date-parts":[[2022,10,3]]},"end":{"date-parts":[[2022,10,5]]}},"container-title":["2022 IEEE Conference on Communications and Network Security (CNS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9947203\/9947223\/09947266.pdf?arnumber=9947266","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T19:57:03Z","timestamp":1670875023000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9947266\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,3]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/cns56114.2022.9947266","relation":{},"subject":[],"published":{"date-parts":[[2022,10,3]]}}}