{"id":"https://openalex.org/W4379874849","doi":"https://doi.org/10.1145/3593013.3594086","title":"Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity","display_name":"Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity","publication_year":2023,"publication_date":"2023-06-12","ids":{"openalex":"https://openalex.org/W4379874849","doi":"https://doi.org/10.1145/3593013.3594086"},"language":"en","primary_location":{"id":"doi:10.1145/3593013.3594086","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3593013.3594086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 ACM Conference on Fairness Accountability and Transparency","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://drum.lib.umd.edu/bitstreams/625be340-61ea-4336-b889-fa250692da01/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076671605","display_name":"Faisal Hamman","orcid":"https://orcid.org/0009-0008-2681-3217"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Faisal Hamman","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Maryland, College Park, USA"],"raw_orcid":"https://orcid.org/0009-0008-2681-3217","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434472","display_name":"Jiahao Chen","orcid":"https://orcid.org/0000-0002-4357-6574"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiahao Chen","raw_affiliation_strings":["Responsible AI LLC, USA"],"raw_orcid":"https://orcid.org/0000-0002-4357-6574","affiliations":[{"raw_affiliation_string":"Responsible AI LLC, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035222388","display_name":"Sanghamitra Dutta","orcid":"https://orcid.org/0000-0002-6500-2627"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanghamitra Dutta","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Maryland, College Park, USA"],"raw_orcid":"https://orcid.org/0000-0002-6500-2627","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076671605"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":0.6816,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74745713,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1358","last_page":"1368"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9995999932289124,"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":0.9995999932289124,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9962000250816345,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7976089715957642},{"id":"https://openalex.org/keywords/audit","display_name":"Audit","score":0.6218289136886597},{"id":"https://openalex.org/keywords/odds","display_name":"Odds","score":0.5202666521072388},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4896464943885803},{"id":"https://openalex.org/keywords/compliance","display_name":"Compliance (psychology)","score":0.4809229075908661},{"id":"https://openalex.org/keywords/threat-model","display_name":"Threat model","score":0.428555428981781},{"id":"https://openalex.org/keywords/information-sensitivity","display_name":"Information sensitivity","score":0.41669952869415283},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.374703586101532},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.36348164081573486},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.30806154012680054},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1459125280380249},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"Logistic regression","score":0.14422887563705444},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.09013751149177551}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7976089715957642},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.6218289136886597},{"id":"https://openalex.org/C143095724","wikidata":"https://www.wikidata.org/wiki/Q515895","display_name":"Odds","level":3,"score":0.5202666521072388},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4896464943885803},{"id":"https://openalex.org/C2781460075","wikidata":"https://www.wikidata.org/wiki/Q1399332","display_name":"Compliance (psychology)","level":2,"score":0.4809229075908661},{"id":"https://openalex.org/C140547941","wikidata":"https://www.wikidata.org/wiki/Q7797194","display_name":"Threat model","level":2,"score":0.428555428981781},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.41669952869415283},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.374703586101532},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.36348164081573486},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.30806154012680054},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1459125280380249},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.14422887563705444},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.09013751149177551},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3593013.3594086","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3593013.3594086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 ACM Conference on Fairness Accountability and Transparency","raw_type":"proceedings-article"},{"id":"pmh:oai:drum.lib.umd.edu:1903/30491","is_oa":true,"landing_page_url":"http://hdl.handle.net/1903/30491","pdf_url":"https://drum.lib.umd.edu/bitstreams/625be340-61ea-4336-b889-fa250692da01/download","source":{"id":"https://openalex.org/S4306401518","display_name":"University Libraries (University of Maryland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"doi:10.13016/dspace/zanj-k2lj","is_oa":true,"landing_page_url":"https://doi.org/10.13016/dspace/zanj-k2lj","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:drum.lib.umd.edu:1903/30491","is_oa":true,"landing_page_url":"http://hdl.handle.net/1903/30491","pdf_url":"https://drum.lib.umd.edu/bitstreams/625be340-61ea-4336-b889-fa250692da01/download","source":{"id":"https://openalex.org/S4306401518","display_name":"University Libraries (University of Maryland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},"sustainable_development_goals":[{"display_name":"Gender equality","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4379874849.pdf","grobid_xml":"https://content.openalex.org/works/W4379874849.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1622686296","https://openalex.org/W1819662813","https://openalex.org/W1873763122","https://openalex.org/W2008732654","https://openalex.org/W2014352947","https://openalex.org/W2015418199","https://openalex.org/W2016127919","https://openalex.org/W2020390700","https://openalex.org/W2027595342","https://openalex.org/W2035458709","https://openalex.org/W2040825624","https://openalex.org/W2051267297","https://openalex.org/W2100960835","https://openalex.org/W2101771965","https://openalex.org/W2119667497","https://openalex.org/W2129131372","https://openalex.org/W2284973007","https://openalex.org/W2346063397","https://openalex.org/W2507358938","https://openalex.org/W2530395818","https://openalex.org/W2550925836","https://openalex.org/W2599025709","https://openalex.org/W2792934256","https://openalex.org/W2797566965","https://openalex.org/W2949804651","https://openalex.org/W2954709318","https://openalex.org/W2959197226","https://openalex.org/W2963392941","https://openalex.org/W2963742154","https://openalex.org/W2965582724","https://openalex.org/W2997892292","https://openalex.org/W3003191700","https://openalex.org/W3018600015","https://openalex.org/W3041537557","https://openalex.org/W3083393236","https://openalex.org/W3100350094","https://openalex.org/W3122083688","https://openalex.org/W3124364623","https://openalex.org/W3125325941","https://openalex.org/W3141602314","https://openalex.org/W3181414820","https://openalex.org/W3192262438","https://openalex.org/W4230692091","https://openalex.org/W4249928010","https://openalex.org/W4250955649","https://openalex.org/W4287588535","https://openalex.org/W4288079548","https://openalex.org/W4288617781","https://openalex.org/W6638208828","https://openalex.org/W6657138077","https://openalex.org/W6728551298","https://openalex.org/W6824583106"],"related_works":["https://openalex.org/W1604849300","https://openalex.org/W4231328776","https://openalex.org/W1604293003","https://openalex.org/W2910024633","https://openalex.org/W1979850356","https://openalex.org/W3005040438","https://openalex.org/W3132387835","https://openalex.org/W1520846789","https://openalex.org/W4229039365","https://openalex.org/W4378191608"],"abstract_inverted_index":{"Existing":[0],"regulations":[1,231,260],"often":[2,40],"prohibit":[3],"model":[4,46,77,125,137,244],"developers":[5,47,78,138,245],"from":[6,152,171,179],"accessing":[7],"protected":[8,34,57,119,142,165,249],"attributes":[9,120,166,250],"(gender,":[10],"race,":[11],"etc.)":[12],"during":[13],"training.":[14],"This":[15],"leads":[16],"to":[17,24,55,67,82,123,219,246,277],"scenarios":[18],"where":[19],"fairness":[20,95,107,211],"assessments":[21],"might":[22,79],"need":[23],"be":[25,80,213],"done":[26],"on":[27,299],"populations":[28],"without":[29],"knowing":[30],"their":[31,50,84],"memberships":[32],"in":[33,148,205],"groups.":[35],"In":[36,97],"such":[37,109,289],"scenarios,":[38],"institutions":[39],"adopt":[41],"a":[42,60,145,154,216,228,267],"separation":[43],"between":[44],"the":[45,56,68,76,90,118,124,136,141,149,164,169,184,187,193,235,243,248,278,291,300],"(who":[48,63],"train":[49],"models":[51,85],"with":[52,222],"no":[53],"access":[54,66],"attributes)":[58],"and":[59,113,190,232,261,303],"compliance":[61,91,221],"team":[62,92],"may":[64],"have":[65],"entire":[69],"dataset":[70,151,189,302,305],"solely":[71],"for":[72,86,93,106,210,242],"auditing":[73],"purposes).":[74],"However,":[75],"allowed":[81],"test":[83,150,188],"disparity":[87],"by":[88,134,274],"querying":[89,105,209],"group":[94,197],"metrics.":[96],"this":[98,256],"paper,":[99],"we":[100,158,263],"first":[101],"demonstrate":[102,128],"that":[103,129,160,270],"simply":[104],"metrics,":[108],"as,":[110],"statistical":[111],"parity":[112],"equalized":[114],"odds":[115],"can":[116,139,162],"leak":[117],"of":[121,144,167,186,195,230,237,251,259,281,308],"individuals":[122,170],"developers.":[126],"We":[127,294],"there":[130],"always":[131],"exist":[132],"strategies":[133],"which":[135],"identify":[140,247],"attribute":[143],"targeted":[146],"individual":[147],"just":[153],"single":[155],"query.":[156],"Furthermore,":[157],"show":[159],"one":[161],"reconstruct":[163],"all":[168],"queries":[172,238],"when":[173],"Nk":[174,191],"\u226a":[175],"n":[176],"using":[177],"techniques":[178,288],"compressed":[180],"sensing":[181],"(n":[182],"is":[183,192,240],"size":[185,194],"smallest":[196],"therein).":[198],"Our":[199],"results":[200,298],"pose":[201],"an":[202],"interesting":[203],"debate":[204],"algorithmic":[206],"fairness:":[207],"Should":[208],"metrics":[212],"viewed":[214],"as":[215,290],"neutral-valued":[217],"solution":[218],"ensure":[220],"regulations?":[223],"Or,":[224],"does":[225],"it":[226],"constitute":[227],"violation":[229,258],"privacy":[233,273],"if":[234],"number":[236],"answered":[239],"enough":[241],"specific":[252],"individuals?":[253],"To":[254],"address":[255],"supposed":[257],"privacy,":[262],"also":[264,295],"propose":[265],"Attribute-Conceal,":[266],"novel":[268],"technique":[269],"achieves":[271],"differential":[272],"calibrating":[275],"noise":[276],"smooth":[279],"sensitivity":[280],"our":[282],"bias":[283],"query":[284],"function,":[285],"outperforming":[286],"naive":[287],"Laplace":[292],"mechanism.":[293],"include":[296],"experimental":[297],"Adult":[301],"synthetic":[304],"(broad":[306],"range":[307],"parameters).":[309]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2023-06-09T00:00:00"}