{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T03:13:59Z","timestamp":1780110839447,"version":"3.54.0"},"reference-count":128,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2017,8,1]],"date-time":"2017-08-01T00:00:00Z","timestamp":1501545600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2017,8,1]],"date-time":"2017-08-01T00:00:00Z","timestamp":1501545600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2017,8,1]],"date-time":"2017-08-01T00:00:00Z","timestamp":1501545600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2017,8,1]],"date-time":"2017-08-01T00:00:00Z","timestamp":1501545600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"US National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1526499"],"award-info":[{"award-number":["IIS-1526499"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"US National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1626432"],"award-info":[{"award-number":["CNS-1626432"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61672313"],"award-info":[{"award-number":["61672313"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61502362"],"award-info":[{"award-number":["61502362"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2017,8,1]]},"DOI":"10.1109\/tkde.2017.2697856","type":"journal-article","created":{"date-parts":[[2017,4,25]],"date-time":"2017-04-25T18:42:40Z","timestamp":1493145760000},"page":"1619-1638","source":"Crossref","is-referenced-by-count":281,"title":["Differentially Private Data Publishing and Analysis: A Survey"],"prefix":"10.1109","volume":"29","author":[{"given":"Tianqing","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanlei","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip S.","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2791347.2791378"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-015-0398-x"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1007\/978-3-642-36594-2_26","article-title":"Analyzing graphs with node differential privacy","author":"kasiviswanathan","year":"2013","journal-title":"Proc Theory Cryptography"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2737785"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2611523"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1250790.1250803"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"341","DOI":"10.14778\/2732269.2732271","article-title":"A data- and workload-aware query answering algorithm for range queries under differential privacy","volume":"7","author":"li","year":"2014","journal-title":"Proc VLDB Endowment"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2010.247"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2465304"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2422436.2422449"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1806689.1806787"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2882928"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.14778\/2732977.2732989"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-013-0309-y"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.14778\/1920841.1920970"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.14778\/2556549.2556576"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783366"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2463721"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1145\/2767007"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2043621.2043626"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-55753-3_36"},{"key":"ref25","first-page":"66","article-title":"Pan-private streaming algorithms","author":"dwork","year":"2010","journal-title":"1st Symp Innovations in Computer Science"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2588573"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783379"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2465330"},{"key":"ref58","article-title":"A theoretical analysis of noisy sparse subspace clustering on dimensionality-reduced data","volume":"abs 1610 7650","author":"wang","year":"2016","journal-title":"CoRR"},{"key":"ref57","first-page":"1000","article-title":"Differentially private subspace clustering","author":"wang","year":"2015","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2015.76"},{"key":"ref55","first-page":"273","article-title":"A practical differentially private random decision tree classifier","volume":"5","author":"jagannathan","year":"2012","journal-title":"Trans Data Privacy"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/1835804.1835868"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/1065167.1065184"},{"key":"ref52","volume":"5","author":"jiawei","year":"2001","journal-title":"Data Mining Concepts and Techniques"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2699501"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-79228-4_1"},{"key":"ref3","first-page":"1","article-title":"Differential privacy","author":"dwork","year":"2006","journal-title":"Proc 33rd Int Conf Automata Languages Program"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1866739.1866758"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973075.16"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1561\/0400000042"},{"key":"ref49","first-page":"361","article-title":"Answering n2+O(1) counting queries with differential privacy is hard","author":"ullman","year":"2013","journal-title":"Proc Annu ACM Symp Theory Comput"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2259911"},{"key":"ref9","first-page":"486","article-title":"Our data, ourselves: Privacy via distributed noise generation","author":"dwork","year":"2006","journal-title":"Proc 24th Annu Int Conf Theory Appl Cryptographic Techn"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2010.12"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2008.27"},{"key":"ref48","first-page":"381","article-title":"On the complexity of differentially private data release: Efficient algorithms and hardness results","author":"dwork","year":"2009","journal-title":"Proc Annu ACM Symp Theory Comput"},{"key":"ref47","first-page":"2348","article-title":"A simple and practical algorithm for differentially private data release","author":"hardt","year":"2012","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.14778\/2535573.2488337"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939818"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020487"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1989323.1989348"},{"key":"ref127","article-title":"Concentrated differential privacy","volume":"abs 1603 1887","author":"dwork","year":"2016","journal-title":"CoRR"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-49096-9_7"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-48995-6_21"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1145\/2090236.2090254"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/2745754.2745755"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2014.56"},{"key":"ref71","first-page":"703","article-title":"Differential privacy for functions and functional data","volume":"14","author":"hall","year":"2013","journal-title":"J Mach Learn Res"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-53641-4_24"},{"key":"ref70","first-page":"118","article-title":"Differentially private learning with kernels","author":"jain","year":"2013","journal-title":"Proc 30th Int Conf Mach Learn"},{"key":"ref76","first-page":"819","article-title":"Differentially private feature selection via stability arguments, and the robustness of the Lasso","author":"thakurta","year":"2013","journal-title":"Proc Conf Learn Theory"},{"key":"ref77","first-page":"476","article-title":"(Near) dimension independent risk bounds for differentially private learning","author":"jain","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3034786.3034795"},{"key":"ref75","first-page":"25.1","article-title":"Private convex optimization for empirical risk minimization with applications to high-dimensional regression","author":"kifer","year":"2012","journal-title":"Proc 25th Annu Conf Learn Theory"},{"key":"ref78","first-page":"488","article-title":"Efficient private empirical risk minimization for high-dimensional learning","author":"kasiviswanathan","year":"2016","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213876"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.14778\/2350229.2350251"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/1835804.1835869"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.14778\/2428536.2428539"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623723"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487601"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2016.7498243"},{"key":"ref67","first-page":"1","article-title":"Learning with differential privacy: Stability, learnability and the sufficiency and necessity of ERM principle","volume":"17","author":"wang","year":"2016","journal-title":"J Mach Learning Res"},{"key":"ref68","first-page":"289","article-title":"Privacy-preserving logistic regression","author":"chaudhuri","year":"2008","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1749603.1749605"},{"key":"ref69","first-page":"1069","article-title":"Differentially private empirical risk minimization","volume":"12","author":"chaudhuri","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-70992-5","volume":"34","author":"aggarwal","year":"2008","journal-title":"Privacy-Preserving Data Mining-Models and Algorithms"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1515\/popets-2016-0015"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.14778\/2732951.2732966"},{"key":"ref108","article-title":"Using randomized response for differential privacy preserving data collection","author":"wang","year":"2016","journal-title":"EDBT\/ICDT Workshops"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.14778\/2809974.2809978"},{"key":"ref107","article-title":"More general queries and less generalization error in adaptive data analysis","volume":"abs 1503 4843","author":"bassily","year":"2015","journal-title":"CoRR"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339564"},{"key":"ref106","article-title":"On the generalization properties of differential privacy","volume":"abs 1504 5800","author":"nissim","year":"2015","journal-title":"CoRR"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25150-9_2"},{"key":"ref105","first-page":"2350","article-title":"Generalization in adaptive data analysis and holdout reuse","author":"dwork","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/MDM.2014.13"},{"key":"ref104","first-page":"117","article-title":"Preserving statistical validity in adaptive data analysis","author":"dwork","year":"2015","journal-title":"Proc Annu ACM Symp Theory Comput"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2012.16"},{"key":"ref103","first-page":"1286","article-title":"Differential privacy with bounded priors: Reconciling utility and privacy in genome-wide association studies","author":"tram\u00e8r","year":"2015","journal-title":"Proc ACM SIGSAC Conf Comput Commun Secur"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487687"},{"key":"ref111","article-title":"LoPub: High-dimensional crowdsourced data publication with local differential privacy","volume":"abs 1612 4350","author":"ren","year":"2016","journal-title":"CoRR"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978409"},{"key":"ref110","article-title":"Collecting and analyzing data from smart device users with local differential privacy","volume":"abs 1606 5053","author":"nguy\u00ean","year":"2016","journal-title":"CoRR"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2013.07.019"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/s11257-016-9177-7"},{"key":"ref96","first-page":"231","author":"calandrino","year":"2011","journal-title":"Proc IEEE Symp Secur Privacy"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557090"},{"key":"ref10","article-title":"Private learning and sanitization: Pure versus approximate differential privacy","volume":"abs 1407 2674","author":"beimel","year":"2014","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2007.66"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1810891.1810916"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1007\/11681878_14","article-title":"Calibrating noise to sensitivity in private data analysis","author":"dwork","year":"2006","journal-title":"Proc Conf Theory of Cryptography"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1374376.1374464"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/773153.773173"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1145\/2514689"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1806689.1806794"},{"key":"ref82","article-title":"Learning in a large function space: Privacy-preserving mechanisms for SVM learning","volume":"abs 911 5708","author":"rubinstein","year":"2009","journal-title":"CoRR"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1145\/2660766"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2010.85"},{"key":"ref81","first-page":"1309","article-title":"Differential privacy preservation for deep auto-encoders: An application of human behavior prediction","author":"phan","year":"2016","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1007\/978-3-642-28914-9_19","article-title":"Iterative constructions and private data release","author":"gupta","year":"2012","journal-title":"Proc Theory Cryptography"},{"key":"ref84","article-title":"Between pure and approximate differential privacy","volume":"abs 1501 6095","author":"steinke","year":"2015","journal-title":"CoRR"},{"key":"ref119","first-page":"747","article-title":"Bayesian differential privacy on correlated data","author":"yang","year":"2015","journal-title":"Proc ACM SIGMOD Int Conf Manage Data"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973402.39"},{"key":"ref83","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/3897.001.0001","author":"kearns","year":"1994","journal-title":"An Introduction to Computational Learning Theory"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2016.7498248"},{"key":"ref113","article-title":"Mutual information optimally local private discrete distribution estimation","volume":"abs 1607 8025","author":"wang","year":"2016","journal-title":"CoRR"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1145\/1989323.1989345"},{"key":"ref80","doi-asserted-by":"crossref","first-page":"1310","DOI":"10.1145\/2810103.2813687","article-title":"Privacy-preserving deep learning","author":"shokri","year":"2015","journal-title":"Proc 22nd ACM SIGSAC Conf Comput Commun Secur"},{"key":"ref115","first-page":"429","article-title":"Local privacy and statistical minimax rates","author":"duchi","year":"2013","journal-title":"Proc Annu IEEE Symp Found Comput Sci"},{"key":"ref120","first-page":"469","article-title":"Reconstruction privacy: Enabling statistical learning","author":"wang","year":"2015","journal-title":"Proc Intl Conf Extending Database Technology"},{"key":"ref89","first-page":"333","article-title":"Mobile systems privacy: ‘MobiPriv’ A robust system for snapshot or continuous querying location based mobile systems","volume":"5","author":"stenneth","year":"2012","journal-title":"Trans Data Privacy"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-013-0344-8"},{"key":"ref122","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1109\/TIFS.2014.2368363","article-title":"Correlated differential privacy: Hiding information in Non-IID data set","volume":"10","author":"zhu","year":"2015","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1145\/2676726.2677000"},{"key":"ref85","first-page":"155","article-title":"Sample complexity bounds for differentially private learning","author":"chaudhuri","year":"2011","journal-title":"Proc Annu Conf Learn Theory"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11799-2_26"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/2422436.2422450"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973730.32"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/ieeexplore.ieee.org\/ielaam\/69\/7970215\/7911185-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/7970215\/07911185.pdf?arnumber=7911185","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,27]],"date-time":"2022-07-27T22:12:29Z","timestamp":1658959949000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7911185\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,8,1]]},"references-count":128,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2017.2697856","relation":{},"ISSN":["1041-4347"],"issn-type":[{"value":"1041-4347","type":"print"}],"subject":[],"published":{"date-parts":[[2017,8,1]]}}}