{"id":"https://openalex.org/W4393159851","doi":"https://doi.org/10.1609/aaai.v38i7.28499","title":"VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models","display_name":"VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models","publication_year":2024,"publication_date":"2024-03-24","ids":{"openalex":"https://openalex.org/W4393159851","doi":"https://doi.org/10.1609/aaai.v38i7.28499"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v38i7.28499","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i7.28499","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28499/28972","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28499/28972","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100710229","display_name":"Ziyi Yin","orcid":"https://orcid.org/0000-0002-5024-8771"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziyi Yin","raw_affiliation_strings":["The Pennsylvania State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024079930","display_name":"Muchao Ye","orcid":"https://orcid.org/0009-0006-9112-8895"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muchao Ye","raw_affiliation_strings":["The Pennsylvania State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020949562","display_name":"Tianrong Zhang","orcid":"https://orcid.org/0000-0003-4958-3393"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianrong Zhang","raw_affiliation_strings":["The Pennsylvania State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365376","display_name":"Jiaqi Wang","orcid":"https://orcid.org/0000-0003-0210-0163"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaqi Wang","raw_affiliation_strings":["The Pennsylvania State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100657632","display_name":"Han Liu","orcid":"https://orcid.org/0009-0000-8384-7933"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Liu","raw_affiliation_strings":["Dalian University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006335513","display_name":"Jinghui Chen","orcid":"https://orcid.org/0000-0002-1486-4526"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinghui Chen","raw_affiliation_strings":["The Pennsylvania State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021459230","display_name":"Ting Wang","orcid":"https://orcid.org/0000-0002-4767-3777"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ting Wang","raw_affiliation_strings":["Stony Brook University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001030192","display_name":"Fenglong Ma","orcid":"https://orcid.org/0000-0002-4999-0303"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fenglong Ma","raw_affiliation_strings":["The Pennsylvania State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"7","first_page":"6755","last_page":"6763"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9969000220298767,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9969000220298767,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9940000176429749,"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/question-answering","display_name":"Question answering","score":0.9097791314125061},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6838459968566895},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5862385630607605},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4847095012664795},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35963010787963867},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3551561236381531}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.9097791314125061},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6838459968566895},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5862385630607605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4847095012664795},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35963010787963867},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3551561236381531}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v38i7.28499","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i7.28499","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28499/28972","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/28499","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/28499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v38i7.28499","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i7.28499","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28499/28972","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1693012609","display_name":"CAREER: Automated Multimodal Learning for Healthcare","funder_award_id":"2238275","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2366221679","display_name":"SaTC: CORE: Small: Attack-Agnostic Defenses against Adversarial Inputs in Learning Systems","funder_award_id":"1953813","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5071890890","display_name":"Collaborative Research: PPoSS: LARGE: Principles and Infrastructure of Extreme Scale Edge Learning for Computational Screening and Surveillance for Health Care","funder_award_id":"2119331","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7501644542","display_name":"III: Small: Usable Interpretability","funder_award_id":"1951729","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":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393159851.pdf"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W1945616565","https://openalex.org/W2250539671","https://openalex.org/W2547875792","https://openalex.org/W2563399268","https://openalex.org/W2640329709","https://openalex.org/W2791683151","https://openalex.org/W2799244840","https://openalex.org/W2891177506","https://openalex.org/W2896457183","https://openalex.org/W2949395487","https://openalex.org/W2950176936","https://openalex.org/W2962847335","https://openalex.org/W2963859254","https://openalex.org/W2963923490","https://openalex.org/W2971970905","https://openalex.org/W2979382951","https://openalex.org/W2984699060","https://openalex.org/W2990753473","https://openalex.org/W2991496458","https://openalex.org/W2995514567","https://openalex.org/W2996851481","https://openalex.org/W3018458867","https://openalex.org/W3020621865","https://openalex.org/W3022021750","https://openalex.org/W3034190247","https://openalex.org/W3086385389","https://openalex.org/W3094950914","https://openalex.org/W3101449015","https://openalex.org/W3119206490","https://openalex.org/W3126792443","https://openalex.org/W3158360872","https://openalex.org/W3169948074","https://openalex.org/W3184735396","https://openalex.org/W3189812816","https://openalex.org/W3208314443","https://openalex.org/W4200634866","https://openalex.org/W4221167445","https://openalex.org/W4229022551","https://openalex.org/W4283317927","https://openalex.org/W4283811884","https://openalex.org/W4287210714","https://openalex.org/W4290944423","https://openalex.org/W4293846201","https://openalex.org/W4299123578","https://openalex.org/W4312715548","https://openalex.org/W4312877428","https://openalex.org/W6640773114","https://openalex.org/W6691431627","https://openalex.org/W6729448088","https://openalex.org/W6754654208","https://openalex.org/W6761041305","https://openalex.org/W6767793131"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3176240006","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4288019534","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"is":[4],"a":[5,33,46,50,73,151,212],"fundamental":[6],"task":[7],"in":[8,174,200,216,231],"computer":[9],"vision":[10],"and":[11,60,84,98,158,179],"natural":[12],"language":[13,93],"process":[14],"fields.":[15],"Although":[16],"the":[17,25,28,66,88,91,99,107,114,131,136,156,163,171,175,194,197,201,217,232],"\u201cpre-training":[18,218],"&":[19,219],"finetuning\u201d":[20],"learning":[21,34],"paradigm":[22,35,221],"significantly":[23],"improves":[24],"VQA":[26,68,187,223],"performance,":[27],"adversarial":[29,57],"robustness":[30],"of":[31,196],"such":[32],"has":[36],"not":[37],"been":[38],"explored.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43,71],"delve":[44],"into":[45],"new":[47],"problem:":[48],"using":[49],"pre-trained":[51],"multimodal":[52],"source":[53,226],"model":[54,94],"to":[55,64,118,128],"create":[56],"image-text":[58],"pairs":[59],"then":[61],"transferring":[62],"them":[63],"attack":[65,97,102,110,145,203],"target":[67],"models.":[69],"Correspondingly,":[70],"propose":[72],"novel":[74],"VQATTACK":[75,199],"model,":[76],"which":[77,154],"can":[78,228],"iteratively":[79],"generate":[80,119],"both":[81,170],"im-":[82],"age":[83],"text":[85,159,164],"perturbations":[86,133,160],"with":[87,189,206],"designed":[89,137],"modules:":[90],"large":[92],"(LLM)-enhanced":[95],"image":[96,109,121,132,157],"cross-modal":[100,143],"joint":[101,144],"module.":[103],"At":[104],"each":[105],"iteration,":[106,153],"LLM-enhanced":[108],"module":[111,146],"first":[112],"optimizes":[113],"latent":[115],"representation-based":[116],"loss":[117],"feature-level":[120],"perturbations.":[122],"Then":[123],"it":[124],"incorporates":[125],"an":[126],"LLM":[127],"further":[129],"enhance":[130],"by":[134],"optimizing":[135],"masked":[138],"answer":[139],"anti-recovery":[140],"loss.":[141],"The":[142,225],"will":[147],"be":[148,229],"triggered":[149],"at":[150],"specific":[152],"updates":[155,166],"sequentially.":[161],"Notably,":[162],"perturbation":[165],"are":[167],"based":[168],"on":[169,185,222],"learned":[172],"gradients":[173],"word":[176,180],"embedding":[177],"space":[178],"synonym-based":[181],"substitution.":[182],"Experimental":[183],"results":[184],"two":[186],"datasets":[188],"five":[190],"validated":[191],"models":[192],"demonstrate":[193],"effectiveness":[195],"proposed":[198],"transferable":[202],"setting,":[204],"compared":[205],"state-of-the-art":[207],"baselines.":[208],"This":[209],"work":[210],"reveals":[211],"significant":[213],"blind":[214],"spot":[215],"fine-tuning\u201d":[220],"tasks.":[224],"code":[227],"found":[230],"link":[233],"https://github.com/ericyinyzy/VQAttack.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}