{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T21:37:00Z","timestamp":1784065020542,"version":"3.55.0"},"reference-count":183,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Tel Aviv University Center for Artificial Intelligence and Data Science"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tkde.2025.3603731","type":"journal-article","created":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T18:11:04Z","timestamp":1756404664000},"page":"6334-6351","source":"Crossref","is-referenced-by-count":5,"title":["Differential Privacy Configurations in the Real World: A Comparative Analysis"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7416-2243","authenticated-orcid":false,"given":"Michael","family":"Khavkin","sequence":"first","affiliation":[{"name":"School of Industrial & Intelligent Systems Engineering, Tel Aviv University, Tel Aviv, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6939-5870","authenticated-orcid":false,"given":"Eran","family":"Toch","sequence":"additional","affiliation":[{"name":"School of Industrial & Intelligent Systems Engineering, Tel Aviv University, Tel Aviv, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/11681878_14"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s40745-023-00475-3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2007.66"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2008.33"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1561\/0400000042"},{"key":"ref6","article-title":"Differential privacy overview","year":"2017"},{"key":"ref7","article-title":"Learning with privacy at scale","year":"2017"},{"key":"ref8","first-page":"3574","article-title":"Collecting telemetry data privately","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ding"},{"key":"ref9","article-title":"Federated learning with formal differential privacy guarantees","author":"McMahan","year":"2022"},{"key":"ref10","article-title":"Google COVID-19 vaccination search insights: Anonymization process description","author":"Bavadekar","year":"2021"},{"key":"ref11","article-title":"Google COVID-19 community mobility reports: Anonymization process description (version 1.1)","author":"Aktay","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-010422-034226"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3226070"},{"key":"ref14","first-page":"1","article-title":"The potential of anonymization method for creating detailed geographical data in Japan","volume":"2019","author":"Ito","year":"2019","journal-title":"Joint UNECE\/Eurostat Work Session Statist. Data Confidentiality"},{"key":"ref15","first-page":"1","article-title":"The potential of differential privacy applied to detailed statistical tables created using microdata from the Japanese population census","volume-title":"Proc. Conf. Eur. Statisticians Expert Meeting Stat. Data Confidentiality","author":"Ito"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/160032"},{"key":"ref17","article-title":"US broadband coverage data set: A differentially private data release","author":"Pereira","year":"2021"},{"key":"ref18","article-title":"Applying energy differential privacy to enable measurement of the OHM connect virtual power plant","author":"Par\u00e9","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.29012\/jpc.689"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-29420-4_3"},{"key":"ref21","first-page":"17","article-title":"Privacy in pharmacogenetics: An end-to-end case study of personalized Warfarin dosing","volume-title":"Proc. 23rd USENIX Secur. Symp.","author":"Fredrikson"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-79228-4_1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/8829523"},{"issue":"1","key":"ref24","first-page":"35","article-title":"Practicing differential privacy in health care: A review","volume":"6","author":"Dankar","year":"2013","journal-title":"Trans. Data Priv."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3073062"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2944748"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3174204"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599561"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3124599"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.101.2100328"},{"key":"ref31","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Statist.","volume":"54","author":"McMahan","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2660267.2660348"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2015.7113353"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3547139"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-26951-7_22"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1536414.1536464"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.29012\/jpc.784"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.2307\/2283137"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1250790.1250803"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.14778\/2350229.2350253"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1536414.1536466"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CSF.2017.11"},{"key":"ref43","article-title":"Concentrated differential privacy","author":"Dwork","year":"2016"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-53641-4_24"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3188745.3188946"},{"key":"ref46","first-page":"547","article-title":"On measures of entropy and information","volume-title":"Proc. 4th Berkeley Symp. Math. Statist. Probab.","author":"R\u00e9nyi"},{"key":"ref47","article-title":"R\u00e9nyi differential privacy of the sampled Gaussian mechanism","author":"Mironov","year":"2019"},{"key":"ref48","first-page":"289","article-title":"Privacy-preserving logistic regression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chaudhuri"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-007-0073-7"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref51","first-page":"1","article-title":"Learning differentially private recurrent language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"McMahan"},{"key":"ref52","article-title":"A list of real-world uses of differential privacy","author":"Desfontaines","year":"2021"},{"key":"ref53","article-title":"Testing privacypreserving telemetry with Prio. Mozilla Hacks","author":"Helmer","year":"2018"},{"key":"ref54","first-page":"5213","article-title":"Practical and private (deep) learning without sampling or shuffling","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Kairouz"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-industry.60"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.14778\/3685800.3685833"},{"key":"ref57","first-page":"259","article-title":"Prio: Private, robust, and scalable computation of aggregate statistics","volume-title":"Proc. 14th USENIX Symp. Netw. Syst. Des. Implementation","author":"Corrigan-Gibbs"},{"key":"ref58","article-title":"Scenes: Differential privacy in action","year":"2023"},{"key":"ref59","article-title":"Publishing Wikipedia usage data with strong privacy guarantees","author":"Adeleye","year":"2023"},{"key":"ref60","article-title":"Geoeditors monthly dataset","year":"2024"},{"key":"ref61","article-title":"Russian editor information (2022\u201323)","year":"2024"},{"key":"ref62","article-title":"Privacy-preserving single post analytics","author":"Rogers","year":"2023"},{"key":"ref63","article-title":"Facebook privacy-protected full URLs data set","author":"Messing","year":"2020"},{"key":"ref64","article-title":"Assistive AI makes replying easier","author":"Microsoft","year":"2021"},{"key":"ref65","article-title":"Federated optimization: Distributed machine learning for on-device intelligence","author":"Kone\u010dn","year":"2016"},{"key":"ref66","article-title":"Predicting text selections with federated learning","author":"Hartmann","year":"2021"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-12809-y"},{"key":"ref68","article-title":"New insights into human mobility with privacy preserving aggregation","author":"Sadilek","year":"2019"},{"key":"ref69","article-title":"Releasing large-scale human mobility histograms with differential privacy","author":"Bian","year":"2024"},{"key":"ref70","article-title":"Uber releases open source project for differential privacy","author":"Tezapsidis","year":"2017"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP48549.2020.00041"},{"key":"ref72","article-title":"Health insurance portability and accountability act of 1996","author":"Department of Health and Human Services","year":"1996"},{"key":"ref73","article-title":"Differential privacy implementation for Hurricane Irma dashboard","year":"2022","journal-title":"Spectus Social Impact"},{"key":"ref74","article-title":"Google COVID-19 search trends symptoms dataset: Anonymization process description (version 1.0)","author":"Bavadekar","year":"2020"},{"key":"ref75","article-title":"Exposure notification privacy-preserving analytics (ENPA), white paper","year":"2021"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2008.4497436"},{"issue":"2","key":"ref77","first-page":"1","article-title":"Releasing earnings distributions using differential privacy: Disclosure avoidance system for post-secondary employment outcomes (PSEO)","volume-title":"J. Privacy Confidentiality","volume":"9","author":"Foote","year":"2019"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.abk3283"},{"key":"ref79","article-title":"Researching formal privacy for the census bureau\u2019s county business patterns program","author":"Sadilek","year":"2023"},{"key":"ref80","article-title":"How Tumult labs helped the IRS support educational accountability with differential privacy","author":"Miklau","year":"2022"},{"key":"ref81","article-title":"Tumult analytics: A robust, easy-to-use, scalable, and expressive framework for differential privacy","author":"Berghel","year":"2022"},{"key":"ref82","article-title":"Applying differential privacy protection to ons mortality data, pilot study","author":"Dove","year":"2021"},{"key":"ref83","article-title":"ABS perturbation methodology through the lens of differential privacy","author":"Bailie","year":"2019"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/sp61157.2025.00101"},{"key":"ref85","article-title":"A members first approach to enabling Linkedin\u2019s labor market insights at scale","author":"Rogers","year":"2020"},{"key":"ref86","article-title":"Privacy-preserving race\/ethnicity estimation for algorithmic bias measurement in the us","author":"Badrinarayanan","year":"2024"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15546-8_11"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24178-9_9"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2977220"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2016.7524458"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/s00450-016-0310-y"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2016.7498248"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/1851182.1851199"},{"key":"ref94","article-title":"Privacy preserving machine learning: Maintaining confidentiality and preserving trust","author":"Ruehle","year":"2021"},{"issue":"371","key":"ref95","first-page":"355","article-title":"A technique to provide differential privacy for appliance usage in smart metering","volume-title":"Inf. Sci.","volume":"370","author":"Barbosa","year":"2016"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.56553\/popets-2023-0045"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/1572532.1572538"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1145\/3614407.3643702"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580791"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/3453158"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1145\/3559104"},{"key":"ref102","article-title":"Improving gboard language models via private federated analytics","author":"Sun","year":"2024"},{"key":"ref103","article-title":"Confidential federated computations","author":"Eichner","year":"2024"},{"key":"ref104","article-title":"Private federated discovery of out-of-vocabulary words for gboard","author":"Sun","year":"2024"},{"key":"ref105","article-title":"Private federated learning in gboard","author":"Zhang","year":"2023"},{"key":"ref106","article-title":"Advances in private training for production on-device language models","author":"Xu","year":"2024"},{"key":"ref107","article-title":"Protecting privacy in Facebook mobility data during the COVID-19 response","author":"Herda\u011fdelen","year":"2020"},{"key":"ref108","article-title":"The global victim-perpetrator synthetic dataset","author":"Gopi","year":"2023"},{"key":"ref109","article-title":"IOM and Microsoft release firstever differentially private synthetic dataset to counter human trafficking","year":"2022"},{"key":"ref110","article-title":"Post-secondary employment outcomes (PSEO)","author":"Foote","year":"2023"},{"key":"ref111","article-title":"Formal privacy guarantees and analytical validity of onthemap public-use data","author":"Andersson","year":"2009"},{"key":"ref112","article-title":"Hurricane irma dashboard","year":"2022"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1145\/3187009.3177733"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1145\/1526709.1526733"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2009.52"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1145\/1651449.1651455"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1145\/1835804.1835869"},{"key":"ref118","first-page":"1876","article-title":"Multiparty differential privacy via aggregation of locally trained classifiers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pathak"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.14778\/1988776.1988780"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339564"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2012.16"},{"key":"ref122","article-title":"Privacy preserving record linkage via grams projections","author":"Bonomi","year":"2012"},{"key":"ref123","first-page":"149","article-title":"DJoin: Differentially private join queries over distributed databases","volume-title":"Proc. 10th USENIX Symp. Operating Syst. Des. Implementation","author":"Narayan"},{"key":"ref124","first-page":"169","article-title":"Towards statistical queries over distributed private user data","volume-title":"Proc. 9th USENIX Symp. Netw. Syst. Des. Implementation","author":"Chen"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.14778\/2168651.2168653"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2011-000459"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2012-001027"},{"key":"ref128","first-page":"2905","article-title":"A near-optimal algorithm for differentially-private principal components","volume":"14","author":"Chaudhuri","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.29012\/jpc.v5i1.629"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1145\/2508859.2516735"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37456-2_28"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-54568-9_13"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1145\/2566486.2568038"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623683"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2014.140"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813640"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/HealthCom.2015.7454576"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2015.2472369"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10165"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-016-0446-0"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978316"},{"key":"ref142","article-title":"Collecting and analyzing data from smart device users with local differential privacy","author":"Nguy\u00ean","year":"2016"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134086"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2773646"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2017.2777862"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132769"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2839752"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.32604\/csse.2018.33.061"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2803782"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2018.00012"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-95729-6_10"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2791588"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00053"},{"key":"ref154","first-page":"164","article-title":"\u201cWhen and where do you want to hide","volume-title":"Proc. IFIP Annu, Conf. Data Appl. Secur. Privacy","author":"Asada"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.2478\/popets-2020-0025"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2899099"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-17138-4_6"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.2478\/popets-2020-0073"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1145\/3314111.3319915"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1016\/j.cels.2020.03.006"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-020-01171-5"},{"key":"ref162","article-title":"Privacy preserving face recognition utilizing differential privacy","volume-title":"Comput. Secur.","volume":"97","author":"Chamikara","year":"2020"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1145\/3397166.3409141"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102767"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.2972001"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2019.2960239"},{"key":"ref167","first-page":"3853","article-title":"Differential privacy for text analytics via natural text sanitization","volume-title":"Proc. Findings Assoc. Comput. Linguistics","author":"Yue"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.14778\/3476249.3476280"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3161544"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2022.2347"},{"key":"ref171","article-title":"Differential privacy for symbolic systems with application to Markov chains","volume-title":"Automatica","volume":"152","author":"Chen","year":"2023"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3241290"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00770"},{"key":"ref174","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.119036","article-title":"Privacy-preserving and traceable federated learning for data sharing in industrial IoT applications","volume":"213","author":"Chen","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref175","first-page":"8561","article-title":"Discrete distribution estimation under user-level local differential privacy","volume-title":"Proc. 26th Int. Conf. Artif. Intell. Statist.","author":"Acharya"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.6233"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.56553\/popets-2023-0086"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119717"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2023.08.010"},{"key":"ref180","article-title":"Multi-tier privacy protection for large language models using differential privacy","author":"Novado","year":"2024","journal-title":"Authorea Preprints"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3391618"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/DCOSS-IoT61029.2024.00012"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1145\/3673971.3673990"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/11197180\/11143893.pdf?arnumber=11143893","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:55:30Z","timestamp":1760032530000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11143893\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":183,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2025.3603731","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}