{"id":"https://openalex.org/W7128309425","doi":"https://doi.org/10.1109/mis.2025.3642664","title":"Evaluating the Adversarial Robustness of Vision\u2013Language Models for Facial Expression Recognition","display_name":"Evaluating the Adversarial Robustness of Vision\u2013Language Models for Facial Expression Recognition","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7128309425","doi":"https://doi.org/10.1109/mis.2025.3642664"},"language":"en","primary_location":{"id":"doi:10.1109/mis.2025.3642664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mis.2025.3642664","pdf_url":null,"source":{"id":"https://openalex.org/S114241109","display_name":"IEEE Intelligent Systems","issn_l":"1541-1672","issn":["1541-1672","1941-1294"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Intelligent Systems","raw_type":"journal-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/A5115902561","display_name":"Hui Kuurila-Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Hui Kuurila-Zhang","raw_affiliation_strings":["University of Oulu, Oulu, Finland"],"affiliations":[{"raw_affiliation_string":"University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125348951","display_name":"Haoyu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Haoyu Chen","raw_affiliation_strings":["University of Oulu, Oulu, Finland"],"affiliations":[{"raw_affiliation_string":"University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123889343","display_name":"Guoying Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Guoying Zhao","raw_affiliation_strings":["University of Oulu, Oulu, Finland"],"affiliations":[{"raw_affiliation_string":"University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5115902561"],"corresponding_institution_ids":["https://openalex.org/I98381234"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3047412,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"41","issue":"1","first_page":"105","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.7423999905586243,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.7423999905586243,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.10440000146627426,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11094","display_name":"Face Recognition and Perception","score":0.06379999965429306,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7099000215530396},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6365000009536743},{"id":"https://openalex.org/keywords/facial-expression-recognition","display_name":"Facial expression recognition","score":0.5376999974250793},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.4830999970436096},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.4821000099182129},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4456999897956848},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.33959999680519104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8080000281333923},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7099000215530396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6452000141143799},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6365000009536743},{"id":"https://openalex.org/C2987714656","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Facial expression recognition","level":4,"score":0.5376999974250793},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.4830999970436096},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.4821000099182129},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4456999897956848},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.383899986743927},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3564000129699707},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.334199994802475},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C56397880","wikidata":"https://www.wikidata.org/wiki/Q6044094","display_name":"Intelligent decision support system","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.27129998803138733}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mis.2025.3642664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mis.2025.3642664","pdf_url":null,"source":{"id":"https://openalex.org/S114241109","display_name":"IEEE Intelligent Systems","issn_l":"1541-1672","issn":["1541-1672","1941-1294"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/212106","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/212106","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5297040343284607}],"awards":[{"id":"https://openalex.org/G1917195477","display_name":null,"funder_award_id":"371019","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G1937205382","display_name":"Towards vision-based emotion AI (EmotionAI)","funder_award_id":"336116","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G3391521669","display_name":null,"funder_award_id":"359894","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G7034793339","display_name":"Towards Moravec's Paradox: Decoding Human Spontaneous Behaviors for Sentient AI from Cognitive Aspects","funder_award_id":"371019","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G7353025116","display_name":null,"funder_award_id":"352788","funder_id":"https://openalex.org/F4320323692","funder_display_name":"Oulun Yliopisto"},{"id":"https://openalex.org/G8709902322","display_name":null,"funder_award_id":"336116","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"},{"id":"https://openalex.org/F4320323692","display_name":"Oulun Yliopisto","ror":"https://ror.org/03yj89h83"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2041616772","https://openalex.org/W2745497104","https://openalex.org/W2889978276","https://openalex.org/W2940983946","https://openalex.org/W4205885905","https://openalex.org/W4386065512","https://openalex.org/W4400527853","https://openalex.org/W4402727057","https://openalex.org/W4402979749","https://openalex.org/W4405717318","https://openalex.org/W4409263369","https://openalex.org/W4416388675"],"related_works":[],"abstract_inverted_index":{"Facial":[0],"expression":[1],"recognition":[2],"(FER)":[3],"using":[4],"vision\u2013language":[5],"models":[6,90],"(VLMs)":[7],"shows":[8],"strong":[9],"performance,":[10],"but":[11],"their":[12],"robustness":[13],"under":[14],"adversarial":[15],"conditions":[16],"is":[17],"underexplored.":[18],"Noting":[19],"that":[20],"most":[21],"VLMs":[22,52,99],"rely":[23],"on":[24,36,71],"CLIP-style":[25],"vision":[26,94,113],"encoders":[27],"vulnerable":[28],"to":[29],"gradient-based":[30,67],"perturbations,":[31],"we":[32,69],"study":[33],"how":[34],"attacks":[35,86],"a":[37,63],"CLIP":[38,64,104],"encoder":[39,114],"affect":[40],"downstream":[41],"recognition.":[42],"We":[43],"test":[44],"zero-shot":[45,80],"classifiers":[46,81],"(CLIP,":[47],"EVA-CLIP,":[48],"Exp-CLIP)":[49],"and":[50,74,96,119],"generative":[51,98],"(BLIP2,":[53],"LLaVA,":[54],"Qwen3-VL)":[55],"performing":[56],"FER":[57,128],"via":[58],"visual":[59],"question":[60],"answering.":[61],"Using":[62],"surrogate":[65],"for":[66,123],"attacks,":[68],"evaluate":[70],"AffectNet,":[72],"RAF-DB,":[73],"FERPlus.":[75],"Key":[76],"findings":[77],"include:":[78],"1)":[79],"are":[82,100],"highly":[83],"fragile,":[84],"2)":[85],"transfer":[87],"only":[88],"between":[89],"sharing":[91],"the":[92,112,116,121],"same":[93],"encoder,":[95],"3)":[97],"more":[101],"robust":[102],"than":[103],"variants":[105],"despite":[106],"task-agnostic":[107],"training.":[108],"These":[109],"results":[110],"identify":[111],"as":[115],"main":[117],"bottleneck":[118],"highlight":[120],"need":[122],"robustness-focused":[124],"design":[125],"in":[126],"future":[127],"systems.":[129]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-02-09T00:00:00"}