{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:49:16Z","timestamp":1781020156889,"version":"3.54.1"},"reference-count":59,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Carl Zeiss Stiftung Research Project \u201cCertification and Foundations of SafeMachine Learning Systems in Healthcare.\u201d"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3603429","type":"journal-article","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T18:32:22Z","timestamp":1756319542000},"page":"151527-151537","source":"Crossref","is-referenced-by-count":6,"title":["Robust Representation Learning for Privacy-Preserving Machine Learning: A Multi-Objective Autoencoder Approach"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0942-3796","authenticated-orcid":false,"given":"Sofiane","family":"Ouaari","sequence":"first","affiliation":[{"name":"Department of Computer Science, Methods in Medical Informatics, University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7279-620X","authenticated-orcid":false,"given":"Ali","family":"Burak \u00dcnal","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Methods in Medical Informatics, University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4088-2784","authenticated-orcid":false,"given":"Mete","family":"Akg\u00fcn","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Methods in Medical Informatics, University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4647-8566","authenticated-orcid":false,"given":"Nico","family":"Pfeifer","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Methods in Medical Informatics, University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813677"},{"key":"ref3","first-page":"9706","article-title":"Variational model inversion attacks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref4","article-title":"Label-only model inversion attack: The attack that requires the least information","author":"Ye","year":"2022","journal-title":"arXiv:2203.06555"},{"key":"ref5","article-title":"Ethical Dimensions of the GDPR","volume-title":"Commentary on the General Data Protection Regulation","author":"Hijmans","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1093\/idpl\/ipab007"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10165"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3338501.3357370"},{"key":"ref10","article-title":"CryptoDL: Deep neural networks over encrypted data","author":"Hesamifard","year":"2017","journal-title":"arXiv:1711.05189"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3159694"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3287564"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52591\/lxai202211289"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2689746.2689747"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/app10165510"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-020-00793-z"},{"key":"ref18","first-page":"1","article-title":"Supervised autoencoders: Improving generalization performance with unsupervised regularizers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Le"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2018.8437533"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892789"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA58266.2023.10248153"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6930"},{"key":"ref24","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":"ref25","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.","author":"Harder"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3460120.3484781"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72744-3_14"},{"key":"ref28","first-page":"4837","article-title":"PrivImage: Differentially private synthetic image generation using diffusion models with semantic-aware pretraining","volume-title":"Proc. 33rd USENIX Secur. Symp.","author":"Li"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_4"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1142\/9789811232701_0003"},{"key":"ref31","first-page":"937","article-title":"Less is more: Revisiting the Gaussian mechanism for differential privacy","volume-title":"Proc. 33rd USENIX Secur. Symp.","author":"Ji"},{"key":"ref32","article-title":"A comparative analysis of word-level metric differential privacy: Benchmarking the privacy-utility trade-off","author":"Meisenbacher","year":"2024","journal-title":"arXiv:2404.03324"},{"key":"ref33","first-page":"5378","article-title":"Privacy for free: How does dataset condensation help privacy?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dong"},{"key":"ref34","article-title":"Dataset condensation with gradient matching","author":"Zhao","year":"2020","journal-title":"arXiv:2006.05929"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3064819"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref38","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2018.02.010"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1089\/cmb.2018.0238"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1186\/1868-7083-6-28"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01520-6"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gky1226"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkz422"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-20430-7"},{"key":"ref46","first-page":"1243","article-title":"Privacy considerations for sharing genomics data","volume":"20","author":"Oestreich","year":"2021","journal-title":"EXCLI J."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2021.103815"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab607"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.4236\/jdaip.2020.84020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ISEMANTIC.2016.7873831"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3390\/s18010018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ISRITI51436.2020.9315510"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.2196\/32903"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ACOMP53746.2021.00017"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.133"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"ref57","first-page":"201","article-title":"Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gilad-Bachrach"},{"key":"ref58","first-page":"51063","article-title":"Heprune: Fast private training of deep neural networks with encrypted data pruning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2024.100689"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11142865.pdf?arnumber=11142865","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T18:24:51Z","timestamp":1757096691000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11142865\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3603429","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}