{"id":"https://openalex.org/W2768087169","doi":"https://doi.org/10.1145/3132847.3132951","title":"Building a Dossier on the Cheap","display_name":"Building a Dossier on the Cheap","publication_year":2017,"publication_date":"2017-11-06","ids":{"openalex":"https://openalex.org/W2768087169","doi":"https://doi.org/10.1145/3132847.3132951","mag":"2768087169"},"language":"en","primary_location":{"id":"doi:10.1145/3132847.3132951","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3132847.3132951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","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/A5085785808","display_name":"Imrul Chowdhury Anindya","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Imrul Chowdhury Anindya","raw_affiliation_strings":["University of Texas at Dallas, Dallas, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Dallas, TX, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026296295","display_name":"Harichandan Roy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harichandan Roy","raw_affiliation_strings":["University of Texas at Dallas, Dallas, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Dallas, TX, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087192873","display_name":"Murat Kantarc\u0131o\u011flu","orcid":"https://orcid.org/0000-0001-9795-9063"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Murat Kantarcioglu","raw_affiliation_strings":["University of Texas at Dallas, Dallas, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Dallas, TX, USA","institution_ids":[]}]},{"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, Nashville, TN, USA"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University, Nashville, TN, USA","institution_ids":["https://openalex.org/I200719446"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5085785808"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.19367418,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1549","last_page":"1558"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9987999796867371,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.975600004196167,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"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/computer-science","display_name":"Computer science","score":0.7916276454925537},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.6778972744941711},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.6192336082458496},{"id":"https://openalex.org/keywords/unique-identifier","display_name":"Unique identifier","score":0.5189928412437439},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5021841526031494},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.47775998711586},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.47657155990600586},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.4701825678348541},{"id":"https://openalex.org/keywords/data-anonymization","display_name":"Data anonymization","score":0.4442991614341736},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.429745078086853},{"id":"https://openalex.org/keywords/liberian-dollar","display_name":"Liberian dollar","score":0.4211839735507965},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.3744104504585266},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3686642646789551},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15816077589988708},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.11756590008735657}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7916276454925537},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.6778972744941711},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.6192336082458496},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.5189928412437439},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5021841526031494},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.47775998711586},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.47657155990600586},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.4701825678348541},{"id":"https://openalex.org/C2776945810","wikidata":"https://www.wikidata.org/wiki/Q17006654","display_name":"Data anonymization","level":3,"score":0.4442991614341736},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.429745078086853},{"id":"https://openalex.org/C109168655","wikidata":"https://www.wikidata.org/wiki/Q242988","display_name":"Liberian dollar","level":2,"score":0.4211839735507965},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.3744104504585266},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3686642646789551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15816077589988708},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.11756590008735657},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3132847.3132951","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3132847.3132951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G329603681","display_name":null,"funder_award_id":"CNS-1111529, CNS-1228198, CICI-1547324, IIS-1633331","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5578097545","display_name":null,"funder_award_id":"1R01HG006844","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W45053571","https://openalex.org/W173470260","https://openalex.org/W1547612978","https://openalex.org/W1972756559","https://openalex.org/W2021679349","https://openalex.org/W2044280769","https://openalex.org/W2054091987","https://openalex.org/W2059554611","https://openalex.org/W2060413568","https://openalex.org/W2104105862","https://openalex.org/W2108991785","https://openalex.org/W2114975469","https://openalex.org/W2115240023","https://openalex.org/W2115826669","https://openalex.org/W2132069633","https://openalex.org/W2159675343","https://openalex.org/W2164456230","https://openalex.org/W2168610667","https://openalex.org/W2172294404","https://openalex.org/W2251214202","https://openalex.org/W2293253366","https://openalex.org/W2905691397","https://openalex.org/W3121289605","https://openalex.org/W4242744113"],"related_works":["https://openalex.org/W2413568490","https://openalex.org/W1913624564","https://openalex.org/W3130054399","https://openalex.org/W2548183822","https://openalex.org/W4294243532","https://openalex.org/W2911599090","https://openalex.org/W2989796854","https://openalex.org/W2141965543","https://openalex.org/W4236766161","https://openalex.org/W2184017202"],"abstract_inverted_index":{"A":[0,38],"wide":[1],"variety":[2],"of":[3,41,126,142,184,191,208,259],"personal":[4,65],"data":[5,52,79,130,140,217,231],"is":[6,48],"routinely":[7],"collected":[8],"by":[9],"numerous":[10],"organizations":[11,84],"that,":[12,45],"in":[13,166],"turn,":[14],"share":[15],"and":[16,98,160,211,237],"sell":[17],"their":[18],"collections":[19],"for":[20,73,186,219],"analytic":[21],"investigations":[22],"(e.g.,":[23,64,71,112],"market":[24],"research).":[25],"To":[26,199],"preserve":[27],"privacy,":[28],"certain":[29,197],"identifiers":[30,63],"are":[31],"often":[32],"redacted,":[33],"perturbed":[34],"or":[35,67],"even":[36,254],"removed.":[37],"substantial":[39],"number":[40],"attacks":[42,96],"have":[43,135,152],"shown":[44],"if":[46],"care":[47],"not":[49],"taken,":[50],"such":[51,95],"can":[53,146,242],"be":[54,110,147,243],"linked":[55,111],"to":[56,59,91,117,137,215,246],"external":[57],"resources":[58,218],"determine":[60],"the":[61,74,78,93,124,187,209,240],"explicit":[62],"names)":[66],"infer":[68],"sensitive":[69,193,250],"attributes":[70,194],"income)":[72],"individuals":[75],"from":[76,158,232],"whom":[77],"was":[80],"collected.":[81],"As":[82],"such,":[83],"increasingly":[85],"rely":[86],"upon":[87],"record":[88],"linkage":[89,103],"methods":[90,104,214,241],"assess":[92],"risk":[94,174],"pose":[97],"adopt":[99],"countermeasures":[100],"accordingly.":[101],"Traditional":[102],"assume":[105],"only":[106],"two":[107,233],"datasets":[108,144,185],"would":[109],"linking":[113],"de-identified":[114],"hospital":[115],"discharge":[116],"identified":[118],"voter":[119,229],"registration":[120,230],"lists),":[121],"but":[122],"with":[123],"advent":[125],"a":[127,138,171,196,205,256],"multi-billion":[128],"dollar":[129],"broker":[131],"industry,":[132],"modern":[133],"adversaries":[134,151,179],"access":[136],"massive":[139],"stash":[141],"multiple":[143],"that":[145,155,239],"leveraged.":[148],"Still,":[149],"realistic":[150],"budget":[153],"constraints":[154],"prevent":[156],"them":[157],"obtaining":[159],"integrating":[161],"all":[162],"relevant":[163],"datasets.":[164],"Thus,":[165],"this":[167,201],"work,":[168],"we":[169,203],"investigate":[170],"novel":[172],"privacy":[173],"assessment":[175],"framework,":[176],"based":[177],"on":[178],"who":[180],"plan":[181],"an":[182,223],"integration":[183],"most":[188],"accurate":[189],"estimate":[190,248],"targeted":[192],"under":[195,255],"budget.":[198],"solve":[200],"problem,":[202],"introduce":[204],"graph-based":[206],"formulation":[207],"problem":[210],"predictive":[212],"modeling":[213],"prioritize":[216],"linkage.":[220],"We":[221],"perform":[222],"empirical":[224],"analysis":[225],"using":[226],"real":[227],"world":[228],"different":[234],"U.S.":[235],"states":[236],"show":[238],"used":[244],"efficiently":[245],"accurately":[247],"potentially":[249],"information":[251],"disclosure":[252],"risks":[253],"non-trivial":[257],"amount":[258],"noise.":[260]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}