{"id":"https://openalex.org/W2555737796","doi":"https://doi.org/10.1109/tkde.2016.2628180","title":"Scalable Iterative Classification for Sanitizing Large-Scale Datasets","display_name":"Scalable Iterative Classification for Sanitizing Large-Scale Datasets","publication_year":2016,"publication_date":"2016-11-11","ids":{"openalex":"https://openalex.org/W2555737796","doi":"https://doi.org/10.1109/tkde.2016.2628180","mag":"2555737796","pmid":"https://pubmed.ncbi.nlm.nih.gov/28943741"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2016.2628180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2016.2628180","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5607782","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100374360","display_name":"Bo Li","orcid":"https://orcid.org/0000-0001-6709-0942"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bo Li","raw_affiliation_strings":["Vanderbilt University","Vanderbilt University, Nashville, TN"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Vanderbilt University, Nashville, TN","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038669899","display_name":"Yevgeniy Vorobeychik","orcid":"https://orcid.org/0000-0003-2471-5345"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yevgeniy Vorobeychik","raw_affiliation_strings":["Vanderbilt University","Vanderbilt University, Nashville, TN"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Vanderbilt University, Nashville, TN","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089917596","display_name":"Muqun Li","orcid":null},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muqun Li","raw_affiliation_strings":["Vanderbilt University","Vanderbilt University, Nashville, TN"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Vanderbilt University, Nashville, TN","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090647314","display_name":"Bradley Malin","orcid":"https://orcid.org/0000-0003-3040-5175"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bradley Malin","raw_affiliation_strings":["Vanderbilt University","Vanderbilt University, Nashville, TN"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Vanderbilt University, Nashville, TN","institution_ids":["https://openalex.org/I200719446"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100374360"],"corresponding_institution_ids":["https://openalex.org/I200719446"],"apc_list":null,"apc_paid":null,"fwci":1.3252,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.8777989,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"29","issue":"3","first_page":"698","last_page":"711"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12034","display_name":"Digital and Cyber Forensics","score":0.9830999970436096,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10237","display_name":"Cryptography and Data Security","score":0.9829000234603882,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8719159364700317},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.761650562286377},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.6525054574012756},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46573343873023987},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.45883315801620483},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45329707860946655},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3678877353668213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34232544898986816},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1950136125087738},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1545695960521698}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8719159364700317},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.761650562286377},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.6525054574012756},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46573343873023987},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.45883315801620483},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45329707860946655},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3678877353668213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34232544898986816},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1950136125087738},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1545695960521698},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tkde.2016.2628180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2016.2628180","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmid:28943741","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28943741","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on knowledge and data engineering","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:5607782","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5607782","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Trans Knowl Data Eng","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:5607782","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5607782","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Trans Knowl Data Eng","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1299527921","display_name":null,"funder_award_id":"N00014-15-1-2621","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G2901424354","display_name":null,"funder_award_id":"IIS-1526860","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2919501389","display_name":null,"funder_award_id":"U01-HG006385","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3319814196","display_name":null,"funder_award_id":"R01-LM011366","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3852472692","display_name":null,"funder_award_id":"R01-LM009989","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4057336105","display_name":null,"funder_award_id":"U01-HG006478","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4385211294","display_name":null,"funder_award_id":"R01-HG006844","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4670170340","display_name":null,"funder_award_id":"W911NF-16-1-0069","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G5078892146","display_name":null,"funder_award_id":"CCF-0424422","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6981798214","display_name":null,"funder_award_id":"FA8785-14-2-0180","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W568984285","https://openalex.org/W992506503","https://openalex.org/W1034374084","https://openalex.org/W1262131959","https://openalex.org/W1524642381","https://openalex.org/W1853481526","https://openalex.org/W1863940422","https://openalex.org/W1966912382","https://openalex.org/W1983459608","https://openalex.org/W2006342960","https://openalex.org/W2021641767","https://openalex.org/W2021679349","https://openalex.org/W2029128277","https://openalex.org/W2030559796","https://openalex.org/W2033092546","https://openalex.org/W2040263621","https://openalex.org/W2040424159","https://openalex.org/W2056354103","https://openalex.org/W2067064328","https://openalex.org/W2069171221","https://openalex.org/W2069870853","https://openalex.org/W2080844952","https://openalex.org/W2101084808","https://openalex.org/W2103528122","https://openalex.org/W2104064500","https://openalex.org/W2109300365","https://openalex.org/W2109426455","https://openalex.org/W2110504778","https://openalex.org/W2111063183","https://openalex.org/W2119047901","https://openalex.org/W2123453946","https://openalex.org/W2128155976","https://openalex.org/W2129749009","https://openalex.org/W2131673214","https://openalex.org/W2132223977","https://openalex.org/W2132678785","https://openalex.org/W2134167315","https://openalex.org/W2140663467","https://openalex.org/W2142406320","https://openalex.org/W2150102617","https://openalex.org/W2156061936","https://openalex.org/W2158645702","https://openalex.org/W2159024459","https://openalex.org/W2160987310","https://openalex.org/W2161229593","https://openalex.org/W2161880183","https://openalex.org/W2166443682","https://openalex.org/W2166656775","https://openalex.org/W2166658587","https://openalex.org/W2168757172","https://openalex.org/W2169818249","https://openalex.org/W2171033594","https://openalex.org/W2183114698","https://openalex.org/W2244344401","https://openalex.org/W2255966483","https://openalex.org/W2285181575","https://openalex.org/W2293768274","https://openalex.org/W2305590176","https://openalex.org/W2460740206","https://openalex.org/W3102994281","https://openalex.org/W3128471160","https://openalex.org/W4234664880","https://openalex.org/W4253730333","https://openalex.org/W4302342646","https://openalex.org/W4399339983","https://openalex.org/W6628254273","https://openalex.org/W6631463386","https://openalex.org/W6638944511","https://openalex.org/W6679204901","https://openalex.org/W6679774445","https://openalex.org/W6681875376","https://openalex.org/W6691930305","https://openalex.org/W6696022951"],"related_works":["https://openalex.org/W2390777183","https://openalex.org/W2461970972","https://openalex.org/W1882848237","https://openalex.org/W2364921833","https://openalex.org/W2388030554","https://openalex.org/W2302028273","https://openalex.org/W4252772812","https://openalex.org/W2385763152","https://openalex.org/W2177394719","https://openalex.org/W63131150"],"abstract_inverted_index":{"Cheap":[0],"ubiquitous":[1],"computing":[2],"enables":[3],"the":[4,86,92,152,191],"collection":[5],"of":[6,9,16,35,88,94,115,190],"massive":[7],"amounts":[8],"personal":[10],"data":[11,24,37,70,90,102,120,167],"in":[12],"a":[13,75,105,109,113,146,156,160,182],"wide":[14],"variety":[15],"domains.":[17],"Many":[18],"organizations":[19],"aim":[20],"to":[21,51,68,84,117,119,139],"share":[22],"such":[23,43,66],"while":[25,186],"obscuring":[26],"features":[27],"that":[28,44,154,171],"could":[29],"disclose":[30],"personally":[31],"identifiable":[32,178],"information.":[33,143],"Much":[34],"this":[36],"exhibits":[38],"weak":[39],"structure":[40],"(e.g.,":[41],"text),":[42],"machine":[45,134],"learning":[46,59,135,184],"approaches":[47,67],"have":[48],"been":[49],"developed":[50],"detect":[52],"and":[53,63,91,121,128,136,194],"remove":[54],"identifiers":[55],"from":[56],"it.":[57],"While":[58],"is":[60,78,83],"never":[61],"perfect,":[62],"relying":[64],"on":[65],"sanitize":[69],"can":[71],"leak":[72],"sensitive":[73,179],"information,":[74],"small":[76],"risk":[77,93],"often":[79],"acceptable.":[80],"Our":[81],"goal":[82],"balance":[85],"value":[87],"published":[89],"an":[95,130],"adversary":[96],"discovering":[97],"leaked":[98,141],"identifiers.":[99],"We":[100,144],"model":[101],"sanitization":[103],"as":[104,126],"game":[106],"between":[107],"1)":[108],"publisher":[110,153],"who":[111,132],"chooses":[112],"set":[114],"classifiers":[116],"apply":[118],"publishes":[122],"only":[123],"instances":[124,180],"predicted":[125],"non-sensitive":[127],"2)":[129],"attacker":[131],"combines":[133],"manual":[137],"inspection":[138],"uncover":[140],"identifying":[142],"introduce":[145],"fast":[147],"iterative":[148],"greedy":[149],"algorithm":[150,173],"for":[151,159,181],"ensures":[155],"low":[157],"utility":[158],"resource-limited":[161],"adversary.":[162],"Moreover,":[163],"using":[164],"five":[165],"text":[166],"sets":[168],"we":[169],"illustrate":[170],"our":[172],"leaves":[174],"virtually":[175],"no":[176],"automatically":[177],"state-of-the-art":[183],"algorithm,":[185],"sharing":[187],"over":[188],"93%":[189],"original":[192],"data,":[193],"completes":[195],"after":[196],"at":[197],"most":[198],"5":[199],"iterations.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}