{"id":"https://openalex.org/W2419749112","doi":"https://doi.org/10.1145/2882903.2915248","title":"PrivateClean","display_name":"PrivateClean","publication_year":2016,"publication_date":"2016-06-14","ids":{"openalex":"https://openalex.org/W2419749112","doi":"https://doi.org/10.1145/2882903.2915248","mag":"2419749112"},"language":"en","primary_location":{"id":"doi:10.1145/2882903.2915248","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2882903.2915248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018480426","display_name":"Sanjay Krishnan","orcid":"https://orcid.org/0000-0001-6968-4090"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sanjay Krishnan","raw_affiliation_strings":["UC Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101850961","display_name":"Jiannan Wang","orcid":"https://orcid.org/0009-0002-8978-312X"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jiannan Wang","raw_affiliation_strings":["Simon Fraser University, Burnaby, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Burnaby, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102019638","display_name":"Michael J. Franklin","orcid":"https://orcid.org/0000-0003-3332-8574"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J. Franklin","raw_affiliation_strings":["UC Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010019244","display_name":"Ken Goldberg","orcid":"https://orcid.org/0000-0001-6747-9499"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ken Goldberg","raw_affiliation_strings":["UC Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034086130","display_name":"Tim Kraska","orcid":"https://orcid.org/0009-0003-2414-2759"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Kraska","raw_affiliation_strings":["Brown University, Providence, RI, USA"],"affiliations":[{"raw_affiliation_string":"Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018480426"],"corresponding_institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":4.7132,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.95298762,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"937","last_page":"951"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":1.0,"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":1.0,"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/T10237","display_name":"Cryptography and Data Security","score":0.9914000034332275,"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/T13048","display_name":"Patient Dignity and Privacy","score":0.9406999945640564,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/differential-privacy","display_name":"Differential privacy","score":0.9381686449050903},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8230941295623779},{"id":"https://openalex.org/keywords/bipartite-graph","display_name":"Bipartite graph","score":0.6347036361694336},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.5892808437347412},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5696192979812622},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5023238658905029},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.44098100066185},{"id":"https://openalex.org/keywords/privacy-protection","display_name":"Privacy protection","score":0.43897753953933716},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40562254190444946},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.40386348962783813},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.17208093404769897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12865036725997925}],"concepts":[{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.9381686449050903},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8230941295623779},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.6347036361694336},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.5892808437347412},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5696192979812622},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5023238658905029},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.44098100066185},{"id":"https://openalex.org/C3017597292","wikidata":"https://www.wikidata.org/wiki/Q25052250","display_name":"Privacy protection","level":2,"score":0.43897753953933716},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40562254190444946},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40386348962783813},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.17208093404769897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12865036725997925}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2882903.2915248","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2882903.2915248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W184146824","https://openalex.org/W192814132","https://openalex.org/W1576945770","https://openalex.org/W1586825695","https://openalex.org/W1610496399","https://openalex.org/W1968201865","https://openalex.org/W1969019410","https://openalex.org/W1974694577","https://openalex.org/W1975184797","https://openalex.org/W1980032585","https://openalex.org/W1982462359","https://openalex.org/W1990503647","https://openalex.org/W2005830269","https://openalex.org/W2012873258","https://openalex.org/W2013666871","https://openalex.org/W2013823004","https://openalex.org/W2022079499","https://openalex.org/W2027595342","https://openalex.org/W2032655922","https://openalex.org/W2041439319","https://openalex.org/W2044102377","https://openalex.org/W2068634907","https://openalex.org/W2071989194","https://openalex.org/W2073479529","https://openalex.org/W2080731889","https://openalex.org/W2091644709","https://openalex.org/W2103133870","https://openalex.org/W2108409407","https://openalex.org/W2110363867","https://openalex.org/W2115240023","https://openalex.org/W2117400432","https://openalex.org/W2119047901","https://openalex.org/W2119167955","https://openalex.org/W2128906841","https://openalex.org/W2134167315","https://openalex.org/W2135930857","https://openalex.org/W2136114025","https://openalex.org/W2142406320","https://openalex.org/W2154721480","https://openalex.org/W2159915142","https://openalex.org/W2167333415","https://openalex.org/W2247123384","https://openalex.org/W2293703278","https://openalex.org/W2296195275","https://openalex.org/W2296272300","https://openalex.org/W2402007731","https://openalex.org/W4205228770","https://openalex.org/W4237961478","https://openalex.org/W4291720518","https://openalex.org/W6607754154","https://openalex.org/W6636177537","https://openalex.org/W6645353459"],"related_works":["https://openalex.org/W3010781909","https://openalex.org/W4200233390","https://openalex.org/W4315705624","https://openalex.org/W2605443953","https://openalex.org/W3116386889","https://openalex.org/W4313218046","https://openalex.org/W2943138144","https://openalex.org/W1604340626","https://openalex.org/W3127289135","https://openalex.org/W3022534164"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,43,101],"differential":[3,22,41],"privacy":[4,11,23,42,86,94],"make":[5],"it":[6],"possible":[7],"to":[8,112,122,130,137,141],"guarantee":[9],"user":[10],"while":[12],"preserving":[13],"the":[14,18,27,35,83,114,142],"main":[15],"characteristics":[16],"of":[17,57,85,99,116,158],"data.":[19],"However,":[20],"most":[21],"mechanisms":[24],"assume":[25],"that":[26],"underlying":[28],"dataset":[29],"is":[30,121],"clean.":[31],"This":[32],"paper":[33],"explores":[34],"link":[36],"between":[37,144],"data":[38,66],"cleaning":[39,145,160],"and":[40,59,68,74,104,133,146,168],"a":[44,51,62,102,124,156],"framework":[45],"we":[46],"call":[47],"PrivateClean.":[48],"PrivateClean":[49],"includes":[50],"technique":[52],"for":[53,64,70],"creating":[54],"private":[55],"datasets":[56,154],"numerical":[58],"discrete-valued":[60],"attributes,":[61],"formalism":[63],"privacy-preserving":[65],"cleaning,":[67],"techniques":[69,161],"answering":[71],"sum,":[72],"count,":[73],"avg":[75],"queries":[76],"after":[77],"cleaning.":[78],"We":[79,148],"show:":[80],"(1)":[81],"how":[82,93,106],"degree":[84,115],"affects":[87],"subsequent":[88],"aggregate":[89],"query":[90],"accuracy,":[91],"(2)":[92],"potentially":[95],"amplifies":[96],"certain":[97],"types":[98],"errors":[100],"dataset,":[103],"(3)":[105],"this":[107,135],"analysis":[108],"can":[109],"be":[110],"used":[111],"tune":[113],"privacy.":[117,147],"The":[118],"key":[119],"insight":[120],"maintain":[123],"bipartite":[125],"graph":[126,136],"relating":[127],"dirty":[128],"values":[129,132],"clean":[131],"use":[134],"estimate":[138],"biases":[139],"due":[140],"interaction":[143],"validate":[149],"these":[150],"results":[151],"on":[152],"four":[153],"with":[155],"variety":[157],"well-studied":[159],"including":[162],"using":[163],"functional":[164],"dependencies,":[165],"outlier":[166],"filtering,":[167],"resolving":[169],"inconsistent":[170],"attributes.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}