{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:20:39Z","timestamp":1783574439581,"version":"3.55.0"},"reference-count":65,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006132","name":"Office of Science","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006132","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006192","name":"Advanced Scientific Computing Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006192","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6,22]]},"DOI":"10.1109\/dsn69566.2026.00051","type":"proceedings-article","created":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T19:41:43Z","timestamp":1783539703000},"page":"448-462","source":"Crossref","is-referenced-by-count":0,"title":["In-Depth Exploration of Differentially Private Quantization for Privacy-Preserving and Communication-Efficient Federated Learning"],"prefix":"10.1109","author":[{"given":"Shan","family":"Huang","sequence":"first","affiliation":[{"name":"Stevens Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhijing","family":"Ye","sequence":"additional","affiliation":[{"name":"Stevens Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiamin","family":"Wang","sequence":"additional","affiliation":[{"name":"Stevens Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaorui","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Fu","sequence":"additional","affiliation":[{"name":"Stevens Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wendy Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"Stevens Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Di","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaodong","family":"Yu","sequence":"additional","affiliation":[{"name":"Stevens Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Artificial intelligence and statistics.","author":"McMahan","year":"2017"},{"key":"ref2","first-page":"5","article-title":"Federated learning: Strategies for improving communication efficiency","volume-title":"Proceedings of the 29th Conference on Neural Information Processing Systems (NIPS)","author":"McMahan"},{"key":"ref3","first-page":"5281","article-title":"FedFa: A fully asynchronous training paradigm for federated learning","volume-title":"Proceedings of the 33rd International Joint Conference on Artificial Intelligence (IJCAI)","author":"Xu"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref5","article-title":"Deep leakage from gradients","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Zhu","year":"2019"},{"key":"ref6","article-title":"idlg: Improved deep leakage from gradients","author":"Zhao","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"ref8","article-title":"Effective passive membership inference attacks in federated learning against overparameterized models","volume-title":"The Eleventh International Conference on Learning Representations","author":"Li"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26122"},{"key":"ref10","article-title":"Threats to federated learning: A survey","author":"Lyu","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/11681878_14"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852172"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356222"},{"key":"ref14","first-page":"4928","article-title":"Terngrad: Ternary gradients to reduce communication in distributed deep learning","volume":"30","author":"Wen","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","first-page":"1709","article-title":"Qsgd: Communication-efficient sgd via gradient quantization and encoding","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"30","author":"Alistarh","year":"2017"},{"key":"ref16","article-title":"signsgd: Compressed optimization for non-convex problems","author":"Bernstein","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16887"},{"key":"ref18","article-title":"cpsgd: Communication-efficient and differentia lly-private distributed sgd","author":"Agarwal","year":"2018"},{"key":"ref19","article-title":"Randomized quantization is all you need for differential privacy in federated learning","author":"Youn","year":"2023"},{"key":"ref20","article-title":"Privacy-aware compression for federated data analysis","volume-title":"Proceedings of the 38th Uncertainty in Artificial Intelligence","volume":"180","author":"Chaudhuri"},{"key":"ref21","first-page":"16937","article-title":"Inverting gradients-how easy is it to break privacy in federated learning?","volume":"33","author":"Geiping","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref22","first-page":"29898","article-title":"Gradient inversion with generative image prior","volume":"34","author":"Jeon","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"Gradient obfuscation gives a false sense of security in federated learning","volume-title":"32nd USENIX Security Symposium (USENIX Security 23)","author":"Yue"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CSF.2018.00027"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3243734.3243855"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jisa.2022.103201"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01922"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JRPROC.1952.273898"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2016.11"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2017.115"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3201176"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cluster48925.2021.00065"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3502181.3531473"},{"key":"ref34","first-page":"581","article-title":"Training quantized nets: A deeper understanding","volume":"30","author":"Hubara","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref35","article-title":"Mixed precision quantization to tackle gradient leakage attacks in federated learning","author":"Ovi","year":"2022"},{"key":"ref36","first-page":"6381","article-title":"Gradient obfuscation gives a false sense of security in federated learning","volume-title":"32nd USENIX Security Symposium (USENIX Security 23)","author":"Yue"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1561\/0400000042"},{"key":"ref38","first-page":"15676","article-title":"The discrete gaussian for differential privacy","volume":"33","author":"Canonne","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref40","article-title":"Renyi differential privacy","volume-title":"CoRR","volume":"abs\/1702.07476","author":"Mironov","year":"2017"},{"key":"ref41","article-title":"CIFAR-10 Dataset","author":"Krizhevsky","year":"2009"},{"key":"ref42","article-title":"LEAF: A benchmark for federated settings","volume-title":"CoRR","volume":"abs\/1812.01097","author":"Caldas","year":"2018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-53641-4_24"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01607"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref46","article-title":"Tiny imagenet visual recognition challenge","year":"2015"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3073804"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1049\/el:20080522"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3659205"},{"key":"ref54","article-title":"Towards federated learning at scale: System design","volume-title":"Proceedings of the 2nd SysML Conference","volume":"2019","author":"Bonawitz"},{"key":"ref55","article-title":"1bit stochastic gradient descent and application to dataparallel distributed training of speech dnns","volume-title":"Fifteenth Annual Conference of the International Speech Communication Association","author":"Seide"},{"key":"ref56","first-page":"14236","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 (NeurIPS)"},{"key":"ref57","first-page":"161","article-title":"Communication-efficient distributed deep learning with error feedback","volume-title":"2016 16th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid).","author":"Dryden"},{"key":"ref58","first-page":"440","article-title":"Sparse communication for distributed gradient descent","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","author":"Aji"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.3046971"},{"key":"ref60","first-page":"2021","article-title":"Fedpaq: A communication-efficient federated learning method with periodic averaging and quantization","volume-title":"Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics","volume":"108","author":"Reisizadeh"},{"key":"ref61","article-title":"Dropout against deep leakage from gradients","author":"Zheng","year":"2021"},{"key":"ref62","article-title":"Enhancing privacy against inversion attacks in federated learning by using mixing gradients strategies","author":"Eloul","year":"2022"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133982"},{"key":"ref64","article-title":"Private federated learning with autotuned compression","author":"Ullah","year":"2023"},{"key":"ref65","first-page":"796","article-title":"Quantization meets differential privacy: A stochastic approach","volume-title":"Proceedings of the 39th International Conference on Machine Learning (ICML)","volume":"162","author":"Wei"}],"event":{"name":"2026 56th Annual IEEE International Conference on Dependable Systems and Networks (DSN)","location":"Charlotte, NC, USA","start":{"date-parts":[[2026,6,22]]},"end":{"date-parts":[[2026,6,25]]}},"container-title":["2026 56th Annual IEEE International Conference on Dependable Systems and Networks (DSN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11593123\/11593173\/11593204.pdf?arnumber=11593204","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:12:33Z","timestamp":1783573953000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11593204\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/dsn69566.2026.00051","relation":{},"subject":[],"published":{"date-parts":[[2026,6,22]]}}}