{"id":"https://openalex.org/W4406460563","doi":"https://doi.org/10.1109/bigdata62323.2024.10825408","title":"Adversarially Exploring Vulnerabilities in LLMs to Evaluate Social Biases","display_name":"Adversarially Exploring Vulnerabilities in LLMs to Evaluate Social Biases","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406460563","doi":"https://doi.org/10.1109/bigdata62323.2024.10825408"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825408","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5015741315","display_name":"Yuya Jeremy Ong","orcid":"https://orcid.org/0000-0002-8591-4455"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuya Jeremy Ong","raw_affiliation_strings":["IBM Research - Almaden,San Jose,California"],"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden,San Jose,California","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024885077","display_name":"Jay Gala","orcid":"https://orcid.org/0009-0001-2894-9897"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jay Gala","raw_affiliation_strings":["IBM Research - Almaden,San Jose,California"],"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden,San Jose,California","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082456601","display_name":"Sungeun An","orcid":"https://orcid.org/0009-0005-1510-6689"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sungeun An","raw_affiliation_strings":["IBM Research - Almaden,San Jose,California"],"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden,San Jose,California","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075524542","display_name":"Robert J. Moore","orcid":"https://orcid.org/0000-0002-5636-9822"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Moore","raw_affiliation_strings":["IBM Research - Almaden,San Jose,California"],"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden,San Jose,California","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029836002","display_name":"Divyesh Jadav","orcid":"https://orcid.org/0000-0002-8602-3689"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Divyesh Jadav","raw_affiliation_strings":["IBM Research - Almaden,San Jose,California"],"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden,San Jose,California","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5015741315"],"corresponding_institution_ids":["https://openalex.org/I4210085935"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28107468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5289","last_page":"5297"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11058","display_name":"Ethics in Business and Education","score":0.9470999836921692,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T11058","display_name":"Ethics in Business and Education","score":0.9470999836921692,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T10734","display_name":"Information and Cyber Security","score":0.9467999935150146,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12519","display_name":"Cybercrime and Law Enforcement Studies","score":0.9348999857902527,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.47280353307724},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.4289800822734833},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.33464741706848145}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47280353307724},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.4289800822734833},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.33464741706848145}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825408","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2781876295","https://openalex.org/W3037831233","https://openalex.org/W3103639864","https://openalex.org/W3105042180","https://openalex.org/W3105882417","https://openalex.org/W3123340107","https://openalex.org/W3135734416","https://openalex.org/W3176477796","https://openalex.org/W3177468621","https://openalex.org/W3207316473","https://openalex.org/W4226040778","https://openalex.org/W4281690148","https://openalex.org/W4285162225","https://openalex.org/W4287854462","https://openalex.org/W4301369855","https://openalex.org/W4304697829","https://openalex.org/W4378189609","https://openalex.org/W4380319657","https://openalex.org/W4384918448","https://openalex.org/W4385570014","https://openalex.org/W4385574250","https://openalex.org/W4388555895","https://openalex.org/W4388787558","https://openalex.org/W4389072555","https://openalex.org/W4390529219","https://openalex.org/W4391420952","https://openalex.org/W4391591738","https://openalex.org/W4392490478","https://openalex.org/W4393146522","https://openalex.org/W4404782667","https://openalex.org/W6799064937","https://openalex.org/W6860759139"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Generative":[0],"AI":[1],"has":[2,17],"caused":[3],"a":[4,157,186,193],"paradigm":[5],"shift":[6],"in":[7,36,39,107,141],"the":[8,41,65,108,117,122,125,162,178],"area":[9],"of":[10,68,105,124,153,180,189],"Artificial":[11],"Intelligence":[12],"(AI)":[13],"and":[14,49,77,82,94,176],"as":[15],"such":[16],"inspired":[18],"much":[19],"new":[20],"research,":[21],"especially":[22],"on":[23,195],"Large":[24],"Language":[25],"Models":[26],"(LLMs).":[27],"LLMs":[28,182],"are":[29,79],"transforming":[30],"how":[31,133],"people":[32],"interact":[33],"with":[34,192,202],"computers":[35],"service-oriented":[37],"fields":[38],"both":[40],"consumer":[42],"(for":[43],"example:":[44],"retail,":[45],"travel,":[46],"education,":[47],"healthcare)":[48],"enterprise":[50],"(customer":[51],"care,":[52],"field":[53],"service,":[54],"sales,":[55],"marketing,":[56],"etc.)":[57],"spaces.":[58],"One":[59],"barrier":[60],"to":[61,90,110,119,121,134,138,161,199],"widespread":[62],"adoption":[63],"is":[64,156],"current":[66],"unpredictability":[67],"LLM":[69,142],"behavior:":[70],"users":[71],"must":[72],"trust":[73,106],"that":[74,86,127],"LLM-based":[75],"services":[76],"systems":[78],"accurate,":[80],"fair,":[81],"unbiased.":[83],"Model":[84],"responses":[85,198],"exhibit":[87],"biases":[88,136],"related":[89,137],"race,":[91],"social":[92,112,139,203],"status,":[93],"other":[95],"sensitive":[96],"topics":[97],"can":[98],"have":[99],"serious":[100],"consequences,":[101],"ranging":[102],"from":[103],"lack":[104],"model":[109,151],"adverse":[111],"implications":[113],"for":[114,174],"consumers,":[115],"all":[116],"way":[118],"damage":[120],"reputations":[123],"corporations":[126],"provide":[128],"them.":[129],"This":[130],"study":[131],"explores":[132],"uncover":[135],"stigmas":[140],"output,":[143],"by":[144],"using":[145],"an":[146,171],"adversarial":[147,190],"prompt-based":[148],"approach.":[149],"Discovering":[150],"vulnerabilities":[152],"this":[154],"type":[155],"nontrivial":[158],"task":[159],"due":[160],"large":[163],"search":[164],"space,":[165],"making":[166],"it":[167],"resource-intensive.":[168],"We":[169,184],"present":[170],"evaluation":[172],"framework":[173],"probing":[175],"analyzing":[177],"behaviors":[179],"multiple":[181],"systematically.":[183],"use":[185],"curated":[187],"set":[188],"prompts":[191,200],"focus":[194],"uncovering":[196],"biased":[197],"associated":[201],"attributes.":[204]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}