{"id":"https://openalex.org/W4388886997","doi":"https://doi.org/10.1145/3605764.3623911","title":"Measuring Equality in Machine Learning Security Defenses: A Case Study in Speech Recognition","display_name":"Measuring Equality in Machine Learning Security Defenses: A Case Study in Speech Recognition","publication_year":2023,"publication_date":"2023-11-21","ids":{"openalex":"https://openalex.org/W4388886997","doi":"https://doi.org/10.1145/3605764.3623911"},"language":"en","primary_location":{"id":"doi:10.1145/3605764.3623911","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3605764.3623911","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.13016/m2u5lz-ufzv","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024890507","display_name":"Luke E. Richards","orcid":"https://orcid.org/0000-0001-5744-8736"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luke E. Richards","raw_affiliation_strings":["University of Maryland, Baltimore County & Pacific Northwest National, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0001-5744-8736","affiliations":[{"raw_affiliation_string":"University of Maryland, Baltimore County & Pacific Northwest National, Baltimore, MD, USA","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068036546","display_name":"Edward Raff","orcid":"https://orcid.org/0000-0002-9900-1972"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward Raff","raw_affiliation_strings":["University of Maryland, Baltimore County, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-9900-1972","affiliations":[{"raw_affiliation_string":"University of Maryland, Baltimore County, Baltimore, MD, USA","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019767181","display_name":"Cynthia Matuszek","orcid":"https://orcid.org/0000-0003-1383-8120"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cynthia Matuszek","raw_affiliation_strings":["University of Maryland, Baltimore County, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0003-1383-8120","affiliations":[{"raw_affiliation_string":"University of Maryland, Baltimore County, Baltimore, MD, USA","institution_ids":["https://openalex.org/I79272384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57780216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"161","last_page":"171"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","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/T11689","display_name":"Adversarial Robustness in Machine Learning","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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9796000123023987,"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":0.7025966048240662},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6880006194114685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5972429513931274},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5946331024169922},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5319716334342957},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.44535452127456665},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4344373941421509},{"id":"https://openalex.org/keywords/harm","display_name":"Harm","score":0.41147202253341675},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.40941378474235535},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.17780596017837524},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1426011025905609}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7025966048240662},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6880006194114685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5972429513931274},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5946331024169922},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5319716334342957},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.44535452127456665},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4344373941421509},{"id":"https://openalex.org/C2777363581","wikidata":"https://www.wikidata.org/wiki/Q15098235","display_name":"Harm","level":2,"score":0.41147202253341675},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.40941378474235535},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.17780596017837524},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1426011025905609},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3605764.3623911","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3605764.3623911","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security","raw_type":"proceedings-article"},{"id":"pmh:oai:mdsoar.org:11603/27040","is_oa":false,"landing_page_url":"http://hdl.handle.net/11603/27040","pdf_url":null,"source":{"id":"https://openalex.org/S4306402556","display_name":"Maryland Shared Open Access Repository (USMAI Consortium)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":null,"raw_type":"Text"},{"id":"doi:10.13016/m2u5lz-ufzv","is_oa":true,"landing_page_url":"https://doi.org/10.13016/m2u5lz-ufzv","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.13016/m2u5lz-ufzv","is_oa":true,"landing_page_url":"https://doi.org/10.13016/m2u5lz-ufzv","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4317134101","display_name":null,"funder_award_id":"2145642,2024878","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2100960835","https://openalex.org/W2525579820","https://openalex.org/W2529337537","https://openalex.org/W2795908329","https://openalex.org/W2963116854","https://openalex.org/W2963689459","https://openalex.org/W3096023981","https://openalex.org/W3130750757","https://openalex.org/W3134501548","https://openalex.org/W3184230132","https://openalex.org/W3211226179","https://openalex.org/W3212960901","https://openalex.org/W3214399478","https://openalex.org/W4226148503","https://openalex.org/W4229336043","https://openalex.org/W4247200422","https://openalex.org/W4287121648","https://openalex.org/W4287323182","https://openalex.org/W4292787090","https://openalex.org/W4296405199","https://openalex.org/W4312940830","https://openalex.org/W4319865458","https://openalex.org/W4323022560","https://openalex.org/W6796638215","https://openalex.org/W6803112758","https://openalex.org/W6804000844"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W4246396837","https://openalex.org/W3176240006","https://openalex.org/W3126451824","https://openalex.org/W2482350142","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4288019534","https://openalex.org/W3105849702"],"abstract_inverted_index":{"Over":[0],"the":[1,4,68,139,199,207,211,214,218,222],"past":[2],"decade,":[3],"machine":[5,72],"learning":[6,73],"security":[7,42,74],"community":[8,23],"has":[9],"developed":[10],"a":[11,120,125,129,179],"myriad":[12],"of":[13,67,71,122,141,147,181,225],"defenses":[14,29,43],"for":[15,25,56,102,134,164,202],"evasion":[16],"attacks.":[17],"An":[18],"understudied":[19],"question":[20,63],"in":[21,45,137,172,213,217],"that":[22,78,81],"is:":[24],"whom":[26],"do":[27],"these":[28],"defend?":[30],"This":[31,205],"work":[32,209],"considers":[33],"common":[34],"approaches":[35],"to":[36,60,109,174,198],"defending":[37],"learned":[38],"systems":[39],"and":[40,58,92,115,128,157,170,189,221],"how":[41,153],"result":[44],"performance":[46],"inequities":[47],"across":[48,167],"different":[49],"sub-populations.":[50],"We":[51,76,118,177],"outline":[52],"appropriate":[53],"parity":[54],"metrics":[55],"analysis":[57],"begin":[59],"answer":[61],"this":[62],"through":[64],"empirical":[65],"results":[66],"fairness":[69,223],"implications":[70],"methods.":[75,117],"find":[77],"many":[79],"methods":[80],"have":[82,159],"been":[83],"proposed":[84],"can":[85,106],"cause":[86],"direct":[87],"harm,":[88],"like":[89],"false":[90],"rejection":[91,116],"unequal":[93],"benefits":[94],"from":[95],"robustness":[96,216],"training.":[97],"The":[98],"framework":[99],"we":[100,151],"propose":[101],"measuring":[103,138],"defense":[104],"equality":[105,140,182],"be":[107],"applied":[108],"robustly":[110],"trained":[111],"models,":[112],"preprocessing-based":[113],"defenses,":[114],"identify":[119],"set":[121],"datasets":[123],"with":[124],"user-centered":[126],"application":[127],"reasonable":[130],"computational":[131],"cost":[132],"suitable":[133],"case":[135,145],"studies":[136],"defenses.":[142,227],"In":[143],"our":[144],"study":[146],"speech":[148,219],"command":[149],"recognition,":[150],"show":[152],"such":[154],"adversarial":[155,215],"training":[156],"augmentation":[158],"non-equal":[160],"but":[161],"complex":[162],"protections":[163],"social":[165],"subgroups":[166],"gender,":[168],"accent,":[169],"age":[171],"relation":[173],"user":[175],"coverage.":[176],"present":[178],"comparison":[180],"between":[183],"two":[184],"rejection-based":[185,226],"defenses:":[186],"randomized":[187,193],"smoothing":[188,194],"neural":[190],"rejection,":[191],"finding":[192],"more":[195],"equitable":[196],"due":[197],"sampling":[200],"mechanism":[201],"minority":[203],"groups.":[204],"represents":[206],"first":[208],"examining":[210],"disparity":[212],"domain":[220],"evaluation":[224]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}