{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T13:26:38Z","timestamp":1740144398750,"version":"3.37.3"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFB3104103"],"award-info":[{"award-number":["2022YFB3104103"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tifs.2024.3516549","type":"journal-article","created":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T19:09:06Z","timestamp":1734030546000},"page":"1011-1022","source":"Crossref","is-referenced-by-count":0,"title":["Privacy-Preserving Generative Modeling With Sliced Wasserstein Distance"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3835-4272","authenticated-orcid":false,"given":"Ziniu","family":"Liu","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5516-5537","authenticated-orcid":false,"given":"Han","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4160-1024","authenticated-orcid":false,"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3335-0093","authenticated-orcid":false,"given":"Aiping","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.58496\/MJCS\/2023\/003"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-014-0506-3"},{"key":"ref4","article-title":"On the convergence and calibration of deep learning with differential privacy","author":"Bu","year":"2021","journal-title":"arXiv:2106.07830"},{"key":"ref5","article-title":"Automatic clipping: Differentially private deep learning made easier and stronger","author":"Bu","year":"2022","journal-title":"arXiv:2206.07136"},{"key":"ref6","first-page":"12480","article-title":"Don\u2019t generate me: Training differentially private generative models with Sinkhorn divergence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Cao"},{"key":"ref7","article-title":"Extracting training data from diffusion models","author":"Carlini","year":"2023","journal-title":"arXiv:2301.13188"},{"key":"ref8","first-page":"12673","article-title":"GS-WGAN: A gradient-sanitized approach for learning differentially private generators","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chen"},{"key":"ref9","article-title":"Augmented sliced Wasserstein distances","author":"Chen","year":"2020","journal-title":"arXiv:2006.08812"},{"key":"ref10","article-title":"Unlocking high-accuracy differentially private image classification through scale","author":"De","year":"2022","journal-title":"arXiv:2204.13650"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01090"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00367"},{"key":"ref13","article-title":"Are diffusion models vulnerable to membership inference attacks?","author":"Duan","year":"2023","journal-title":"arXiv:2302.01316"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/11681878_14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1561\/9781601988195"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref17","first-page":"1819","article-title":"DP-MERF: Differentially private mean embeddings with RandomFeatures for practical privacy-preserving data generation","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","volume":"130","author":"Harder"},{"article-title":"PATE-GAN: Generating synthetic data with differential privacy guarantees","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Jordon","key":"ref18"},{"key":"ref19","first-page":"261","article-title":"Generalized sliced Wasserstein distances","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kolouri"},{"article-title":"Sliced Wasserstein auto-encoders","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kolouri","key":"ref20"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"article-title":"Large language models can be strong differentially private learners","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00036"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2827163"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref27","first-page":"2965","article-title":"G-pate: Scalable differentially private data generator via private aggregation of teacher discriminators","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Long"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SPW59333.2023.00013"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CSF.2017.11"},{"key":"ref30","article-title":"Distributional sliced-Wasserstein and applications to generative modeling","author":"Nguyen","year":"2020","journal-title":"arXiv:2002.07367"},{"key":"ref31","first-page":"1","article-title":"Semi-supervised knowledge transfer for deep learning from private training data","volume-title":"Proc. 5th Int. Conf. Learn. Represent.","author":"Papernot"},{"article-title":"Scalable private learning with PATE","volume-title":"Proc. 6th Int. Conf. Learn. Represent.","author":"Papernot","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1561\/2200000073"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24785-9_37"},{"issue":"21","key":"ref35","first-page":"124","article-title":"1.1 \u00fcber die bestimmung von funktionen durch ihre integralwerte l\u00e4ngs gewisser mannigfaltigkeiten","volume-title":"Classic Papers Modern Diagnostic Radiol.","volume":"5","author":"Radon"},{"key":"ref36","first-page":"8810","article-title":"Differentially private sliced Wasserstein distance","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rakotomamonjy"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.5804"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00018"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-71050-9","volume-title":"Optimal Transport: Old and New","volume":"338","author":"Villani","year":"2009"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3460120.3484579"},{"key":"ref42","first-page":"1226","article-title":"Subsampled r\u00e9nyi differential privacy and analytical moments accountant","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","author":"Wang"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00383"},{"key":"ref44","article-title":"Membership inference attacks against text-to-image generation models","author":"Wu","year":"2022","journal-title":"arXiv:2210.00968"},{"key":"ref45","article-title":"Differentially private generative adversarial network","author":"Xie","year":"2018","journal-title":"arXiv:1802.06739"},{"key":"ref46","article-title":"LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop","author":"Yu","year":"2015","journal-title":"arXiv:1506.03365"},{"key":"ref47","first-page":"1","article-title":"Poission subsampled r\u00e9nyi differential privacy","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10206\/10810755\/10795203.pdf?arnumber=10795203","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T19:44:11Z","timestamp":1736883851000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10795203\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/tifs.2024.3516549","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"type":"print","value":"1556-6013"},{"type":"electronic","value":"1556-6021"}],"subject":[],"published":{"date-parts":[[2025]]}}}