{"id":"https://openalex.org/W4386815481","doi":"https://doi.org/10.14428/esann/2023.es2023-182","title":"Adversarial Auditing of Machine Learning Models under Compound Shift","display_name":"Adversarial Auditing of Machine Learning Models under Compound Shift","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386815481","doi":"https://doi.org/10.14428/esann/2023.es2023-182"},"language":"en","primary_location":{"id":"doi:10.14428/esann/2023.es2023-182","doi":"https://doi.org/10.14428/esann/2023.es2023-182","is_oa":true,"landing_page_url":"http://doi.org/10.14428/esann/2023.es2023-182","pdf_url":"https://doi.org/10.14428/esann/2023.es2023-182","source":{"id":"https://openalex.org/S7407087818","display_name":"European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.14428/esann/2023.es2023-182","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070426983","display_name":"Karan Bhanot","orcid":"https://orcid.org/0000-0003-4791-5796","observed_orcids":["https://orcid.org/0000-0003-4791-5796"]},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karan Bhanot","raw_affiliation_strings":["- Rensselaer Polytechnic Institute - Department of Computer Science - New York - USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"- Rensselaer Polytechnic Institute - Department of Computer Science - New York - USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103053820","display_name":"Dennis Wei","orcid":"https://orcid.org/0000-0002-6510-1537","observed_orcids":["https://orcid.org/0000-0002-6510-1537"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dennis Wei","raw_affiliation_strings":["-IBM Research -Yorktown Heights, New York -USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"-IBM Research -Yorktown Heights, New York -USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073341059","display_name":"Ioana Baldini","orcid":"https://orcid.org/0000-0002-8257-9866","observed_orcids":["https://orcid.org/0000-0002-8257-9866"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ioana Baldini","raw_affiliation_strings":["-IBM Research -Yorktown Heights, New York -USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"-IBM Research -Yorktown Heights, New York -USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048876983","display_name":"Kristin P. Bennett","orcid":"https://orcid.org/0000-0002-8782-105X","observed_orcids":["https://orcid.org/0000-0002-8782-105X"]},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristin Bennett","raw_affiliation_strings":["- Rensselaer Polytechnic Institute - Department of Mathematics - New York - USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"- Rensselaer Polytechnic Institute - Department of Mathematics - New York - USA","institution_ids":["https://openalex.org/I165799507"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18330072,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"217","last_page":"222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.8008000254631042,"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"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.8008000254631042,"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":0.0640999972820282,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.06069999933242798,"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/algorithmic-fairness","display_name":"algorithmic fairness","score":0.621999979019165},{"id":"https://openalex.org/keywords/distribution-shift","display_name":"distribution shift","score":0.8199999928474426},{"id":"https://openalex.org/keywords/fairness-utility-trade-off","display_name":"fairness-utility trade-off","score":0.7540000081062317},{"id":"https://openalex.org/keywords/multi-objective-bayesian-optimization","display_name":"multi-objective Bayesian optimization","score":0.9449999928474426},{"id":"https://openalex.org/keywords/protected-characteristics","display_name":"protected characteristics","score":0.7760000228881836},{"id":"https://openalex.org/keywords/fairness-audits","display_name":"fairness auditing","score":0.35199999809265137}],"concepts":[{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.7739471197128296},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6980064511299133},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6131173372268677},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5960860252380371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.525750458240509},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5188604593276978},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.49186182022094727},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.45368728041648865},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.1445908546447754},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.134131520986557},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14428/esann/2023.es2023-182","doi":"https://doi.org/10.14428/esann/2023.es2023-182","is_oa":true,"landing_page_url":"http://doi.org/10.14428/esann/2023.es2023-182","pdf_url":"https://doi.org/10.14428/esann/2023.es2023-182","source":{"id":"https://openalex.org/S7407087818","display_name":"European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.14428/esann/2023.es2023-182","doi":"https://doi.org/10.14428/esann/2023.es2023-182","is_oa":true,"landing_page_url":"http://doi.org/10.14428/esann/2023.es2023-182","pdf_url":"https://doi.org/10.14428/esann/2023.es2023-182","source":{"id":"https://openalex.org/S7407087818","display_name":"European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386815481.pdf","grobid_xml":"https://content.openalex.org/works/W4386815481.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2170612786","https://openalex.org/W2396881363","https://openalex.org/W2530395818","https://openalex.org/W2959197226","https://openalex.org/W3007501395","https://openalex.org/W3035677605","https://openalex.org/W3105441357","https://openalex.org/W3162387221","https://openalex.org/W6888840370"],"related_works":["https://openalex.org/W7167800435","https://openalex.org/W7123273274","https://openalex.org/W7015133832","https://openalex.org/W4385484657","https://openalex.org/W7215032912","https://openalex.org/W4409347365","https://openalex.org/W7138972893","https://openalex.org/W3012438081","https://openalex.org/W3141587971","https://openalex.org/W4295103037"],"abstract_inverted_index":{"Machine":[0],"learning":[1],"(ML)":[2],"models":[3,31],"often":[4],"perform":[5],"differently":[6],"under":[7,32],"distribution":[8],"shifts,":[9],"in":[10,76],"terms":[11],"of":[12,29,35,86],"utility,":[13],"fairness,":[14],"and":[15,26,37,50,60,73,94],"other":[16],"dimensions.We":[17],"propose":[18],"the":[19,24,84],"Adversarial":[20],"Auditor":[21],"for":[22,47,90],"measuring":[23],"utility":[25],"fairness":[27],"performance":[28,55],"ML":[30],"compound":[33],"shifts":[34,52],"outcome":[36],"protected":[38],"attributes.We":[39],"use":[40],"Multi-Objective":[41],"Bayesian":[42],"Optimization":[43],"(MOBO)":[44],"to":[45],"account":[46],"multiple":[48],"metrics":[49],"identify":[51],"where":[53],"model":[54],"is":[56],"extreme,":[57],"both":[58],"good":[59],"bad.Using":[61],"two":[62],"case":[63],"studies,":[64],"we":[65],"show":[66],"that":[67],"MOBO":[68],"performed":[69],"better":[70],"than":[71],"random":[72],"grid-based":[74],"approaches":[75],"identifying":[77],"scenarios":[78],"by":[79],"adversarially":[80],"optimizing":[81],"objectives,":[82],"highlighting":[83],"value":[85],"such":[87],"an":[88],"auditor":[89],"developing":[91],"fair,":[92],"accurate":[93],"shift-robust":[95],"models.":[96]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2023-09-18T00:00:00"}