{"id":"https://openalex.org/W3134501548","doi":"https://doi.org/10.1145/3442188.3445910","title":"Fairness Through Robustness","display_name":"Fairness Through Robustness","publication_year":2021,"publication_date":"2021-02-25","ids":{"openalex":"https://openalex.org/W3134501548","doi":"https://doi.org/10.1145/3442188.3445910","mag":"3134501548"},"language":"en","primary_location":{"id":"doi:10.1145/3442188.3445910","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3442188.3445910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency","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/A5048896019","display_name":"Vedant Nanda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vedant Nanda","raw_affiliation_strings":["University of Maryland MPI-SWS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland MPI-SWS","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063355813","display_name":"Samuel Dooley","orcid":"https://orcid.org/0000-0001-8598-7681"},"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":"Samuel Dooley","raw_affiliation_strings":["University of Maryland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078010312","display_name":"Sahil Singla","orcid":"https://orcid.org/0000-0002-8800-6479"},"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":"Sahil Singla","raw_affiliation_strings":["University of Maryland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025450606","display_name":"Soheil Feizi","orcid":"https://orcid.org/0000-0003-0944-8242"},"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":"Soheil Feizi","raw_affiliation_strings":["University of Maryland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071538560","display_name":"John P. Dickerson","orcid":"https://orcid.org/0000-0003-2231-680X"},"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":"John P. Dickerson","raw_affiliation_strings":["University of Maryland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.4369,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.97086416,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"466","last_page":"477"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9969000220298767,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9666000008583069,"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/robustness","display_name":"Robustness (evolution)","score":0.7795361280441284},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7485641837120056},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5746866464614868},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.560736358165741},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5170872211456299},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4986705780029297},{"id":"https://openalex.org/keywords/harm","display_name":"Harm","score":0.4299486577510834},{"id":"https://openalex.org/keywords/decision-boundary","display_name":"Decision boundary","score":0.4281769096851349},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42411941289901733},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0872708261013031},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.08566528558731079}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7795361280441284},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7485641837120056},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5746866464614868},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.560736358165741},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5170872211456299},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4986705780029297},{"id":"https://openalex.org/C2777363581","wikidata":"https://www.wikidata.org/wiki/Q15098235","display_name":"Harm","level":2,"score":0.4299486577510834},{"id":"https://openalex.org/C42023084","wikidata":"https://www.wikidata.org/wiki/Q5249231","display_name":"Decision boundary","level":3,"score":0.4281769096851349},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42411941289901733},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0872708261013031},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08566528558731079},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3442188.3445910","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3442188.3445910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"},{"score":0.46000000834465027,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W1596717185","https://openalex.org/W1686810756","https://openalex.org/W1945616565","https://openalex.org/W1965804146","https://openalex.org/W2014352947","https://openalex.org/W2087347434","https://openalex.org/W2100960835","https://openalex.org/W2180612164","https://openalex.org/W2194775991","https://openalex.org/W2243397390","https://openalex.org/W2502094132","https://openalex.org/W2592232824","https://openalex.org/W2593390416","https://openalex.org/W2612690371","https://openalex.org/W2624319794","https://openalex.org/W2730550703","https://openalex.org/W2732560823","https://openalex.org/W2773523653","https://openalex.org/W2787955716","https://openalex.org/W2787991113","https://openalex.org/W2788481061","https://openalex.org/W2790697880","https://openalex.org/W2794342582","https://openalex.org/W2804815760","https://openalex.org/W2808241018","https://openalex.org/W2810290439","https://openalex.org/W2889295596","https://openalex.org/W2904642422","https://openalex.org/W2911634294","https://openalex.org/W2920646515","https://openalex.org/W2943927551","https://openalex.org/W2951735139","https://openalex.org/W2962971773","https://openalex.org/W2963446712","https://openalex.org/W2963611658","https://openalex.org/W2963808661","https://openalex.org/W2963857521","https://openalex.org/W2964031043","https://openalex.org/W2970971581","https://openalex.org/W2990594575","https://openalex.org/W2992319600","https://openalex.org/W3004604609","https://openalex.org/W3013571594","https://openalex.org/W3029730229","https://openalex.org/W3034214983","https://openalex.org/W3034700241","https://openalex.org/W3037294637","https://openalex.org/W3099361686","https://openalex.org/W3102518922","https://openalex.org/W3103340107","https://openalex.org/W3104475013","https://openalex.org/W3111128105","https://openalex.org/W3121588992","https://openalex.org/W3172707490","https://openalex.org/W4287814952","https://openalex.org/W4288359825","https://openalex.org/W4294972627","https://openalex.org/W4300482433","https://openalex.org/W6637162671","https://openalex.org/W6638208828","https://openalex.org/W6684072790","https://openalex.org/W6728551298","https://openalex.org/W6751895977","https://openalex.org/W6752279996","https://openalex.org/W6765646913","https://openalex.org/W6774549192","https://openalex.org/W6776192123","https://openalex.org/W7014198846"],"related_works":["https://openalex.org/W2950183588","https://openalex.org/W4322759769","https://openalex.org/W4286235935","https://openalex.org/W3094843325","https://openalex.org/W3207178610","https://openalex.org/W4365420856","https://openalex.org/W4382763378","https://openalex.org/W4288362200","https://openalex.org/W3072584680","https://openalex.org/W4311734044"],"abstract_inverted_index":{"Deep":[0],"neural":[1,136],"networks":[2,137],"(DNNs)":[3],"are":[4,64,70,158,172,176],"increasingly":[5],"used":[6,140],"in":[7,16,84,100,153,205],"real-world":[8,141,233],"applications":[9],"(e.g.":[10],"facial":[11],"recognition).":[12],"This":[13],"has":[14],"resulted":[15],"concerns":[17],"about":[18],"the":[19,51,74,192,196,201,206],"fairness":[20,32,62],"of":[21,31,50,61,103,126,186,200,208,213],"decisions":[22],"made":[23],"by":[24],"these":[25],"models.":[26],"Various":[27],"notions":[28,60],"and":[29,118,148,150,175,195],"measures":[30],"have":[33],"been":[34],"proposed":[35],"to":[36,78,94,122,190,229,243],"ensure":[37],"that":[38,58,63,83,108,152,183,222,235],"a":[39,96,101,113,179,216],"decision-making":[40],"system":[41],"does":[42],"not":[43,71],"disproportionately":[44],"harm":[45],"(or":[46],"benefit)":[47],"particular":[48,97],"subgroups":[49,159],"population.":[52],"In":[53],"this":[54,124,184],"paper,":[55],"we":[56],"argue":[57,82,182],"traditional":[59],"only":[65],"based":[66,163],"on":[67,134,138,164,237],"models'":[68],"outputs":[69],"sufficient":[72],"when":[73],"model":[75],"is":[76,112,225],"vulnerable":[77],"adversarial":[79],"attacks.":[80],"We":[81,106,128,181],"some":[85,161],"cases,":[86],"it":[87],"may":[88],"be":[89,249],"easier":[90],"for":[91,116,239],"an":[92,131,226],"attacker":[93],"target":[95],"subgroup,":[98],"resulting":[99],"form":[102,125],"robustness":[104,110,223],"bias.":[105,127],"show":[107,151,221],"measuring":[109],"bias":[111,187,224],"challenging":[114],"task":[115],"DNNs":[117,238],"propose":[119],"two":[120],"methods":[121],"measure":[123],"then":[129],"conduct":[130],"empirical":[132],"study":[133],"state-of-the-art":[135],"commonly":[139],"datasets":[142],"such":[143,214],"as":[144],"CIFAR-10,":[145],"CIFAR-100,":[146],"Adience,":[147],"UTKFace":[149],"almost":[154],"all":[155,245],"cases":[156,162],"there":[157],"(in":[160],"sensitive":[165],"attributes":[166],"like":[167],"race,":[168],"gender,":[169],"etc)":[170],"which":[171],"less":[173],"robust":[174],"thus":[177,210],"at":[178],"disadvantage.":[180],"kind":[185],"arises":[188],"due":[189],"both":[191],"data":[193],"distribution":[194],"highly":[197],"complex":[198],"nature":[199],"learned":[202],"decision":[203,240],"boundary":[204],"case":[207],"DNNs,":[209],"making":[211],"mitigation":[212],"biases":[215],"non-trivial":[217],"task.":[218],"Our":[219],"results":[220,247],"important":[227],"criterion":[228],"consider":[230],"while":[231],"auditing":[232],"systems":[234],"rely":[236],"making.":[241],"Code":[242],"reproduce":[244],"our":[246],"can":[248],"found":[250],"here:":[251],"https://github.com/nvedant07/Fairness-Through-Robustness":[252]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":12}],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2025-10-10T00:00:00"}