{"id":"https://openalex.org/W7128728883","doi":"https://doi.org/10.1109/tcsvt.2026.3664103","title":"GIGAS: Adversarial Attacks on Visual Question Answering With Multi-Modal Generative Models","display_name":"GIGAS: Adversarial Attacks on Visual Question Answering With Multi-Modal Generative Models","publication_year":2026,"publication_date":"2026-02-12","ids":{"openalex":"https://openalex.org/W7128728883","doi":"https://doi.org/10.1109/tcsvt.2026.3664103"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3664103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3664103","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Transactions on Circuits and Systems for Video Technology","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/A5100314566","display_name":"Yunxuan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunxuan Li","raw_affiliation_strings":["Institute of Artificial Intelligence, Shanghai University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125711094","display_name":"Jing Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Yu","raw_affiliation_strings":["School of Information Engineering, Minzu University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3966-511X","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125762284","display_name":"Tieyong Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tieyong Zeng","raw_affiliation_strings":["Department of Mathematics, The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-0688-202X","affiliations":[{"raw_affiliation_string":"Department of Mathematics, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125688951","display_name":"Yang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhou","raw_affiliation_strings":["School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5828-2659","affiliations":[{"raw_affiliation_string":"School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086395002","display_name":"Ling Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyan Ma","raw_affiliation_strings":["Institute of Artificial Intelligence, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8377-0163","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14366191,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"6","first_page":"8385","last_page":"8397"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7861999869346619,"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":0.7861999869346619,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.06930000334978104,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.06480000168085098,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.8629999756813049},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.7283999919891357},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6890000104904175},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5041000247001648},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.48989999294281006},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4058000147342682},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3743000030517578},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.34459999203681946}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8629999756813049},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.796500027179718},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.7283999919891357},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6890000104904175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5375999808311462},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5041000247001648},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.48989999294281006},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4489000141620636},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4058000147342682},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3743000030517578},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.34459999203681946},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3379000127315521},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.30730000138282776},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C2778403875","wikidata":"https://www.wikidata.org/wiki/Q20312394","display_name":"Adversarial machine learning","level":3,"score":0.29600000381469727},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C65856478","wikidata":"https://www.wikidata.org/wiki/Q3991682","display_name":"Attack model","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.2680000066757202},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3664103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3664103","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2241173898","display_name":null,"funder_award_id":"2022ZD0160603","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2243397390","https://openalex.org/W2560730294","https://openalex.org/W2774644650","https://openalex.org/W2799244840","https://openalex.org/W2891177506","https://openalex.org/W2905526464","https://openalex.org/W2949128310","https://openalex.org/W2950733407","https://openalex.org/W2962782614","https://openalex.org/W2962818281","https://openalex.org/W2963165363","https://openalex.org/W2963448658","https://openalex.org/W2963518342","https://openalex.org/W3011813266","https://openalex.org/W3034190247","https://openalex.org/W3101449015","https://openalex.org/W3103934057","https://openalex.org/W3159619744","https://openalex.org/W3186991201","https://openalex.org/W3204281258","https://openalex.org/W4214764354","https://openalex.org/W4221155360","https://openalex.org/W4283317927","https://openalex.org/W4285605365","https://openalex.org/W4293846201","https://openalex.org/W4296079585","https://openalex.org/W4360884927","https://openalex.org/W4361991035","https://openalex.org/W4382998936","https://openalex.org/W4385245566","https://openalex.org/W4385572035","https://openalex.org/W4386076525","https://openalex.org/W4390872540","https://openalex.org/W4390872600","https://openalex.org/W4390872822","https://openalex.org/W4390874153","https://openalex.org/W4390889737","https://openalex.org/W4390889750","https://openalex.org/W4393148220","https://openalex.org/W4393159851","https://openalex.org/W4402288734","https://openalex.org/W4402715899","https://openalex.org/W4404356490","https://openalex.org/W4406110392","https://openalex.org/W4407097622","https://openalex.org/W4407449622","https://openalex.org/W4408029987","https://openalex.org/W4409261999","https://openalex.org/W4413169625","https://openalex.org/W7133193597","https://openalex.org/W7133196460","https://openalex.org/W7133197087","https://openalex.org/W7133197604","https://openalex.org/W7133241479","https://openalex.org/W7160178179"],"related_works":[],"abstract_inverted_index":{"VQA":[0,42,197],"models,":[1],"which":[2],"answer":[3],"questions":[4],"about":[5],"images":[6,139],"by":[7,141],"combining":[8],"both":[9],"visual":[10,133],"and":[11,93,160,171,196,223],"textual":[12],"information,":[13],"have":[14,57,72],"been":[15],"proven":[16],"susceptible":[17],"to":[18,26,30,76,117,126,145,152,163],"adversarial":[19,39,100,132,155],"attacks.":[20],"These":[21],"attacks":[22,40,71],"introduce":[23],"subtle":[24],"perturbations":[25],"the":[27,32,46,63,85,88,96,184,187],"input":[28],"data":[29],"manipulate":[31],"model\u2019s":[33],"predictions.":[34],"This":[35],"paper":[36],"focuses":[37],"on":[38,166,180,192,209],"targeting":[41],"models":[43,116,144,195,222],"that":[44,53,112],"follow":[45],"\u201cpre-training":[47],"&":[48],"fine-tuning\u201d":[49],"paradigm,":[50],"an":[51,109,204],"area":[52],"remains":[54],"under-explored.":[55],"We":[56],"identified":[58],"two":[59],"key":[60,123],"issues":[61],"in":[62],"current":[64],"field.":[65],"On":[66,84],"one":[67],"hand,":[68,87],"existing":[69],"multi-modal":[70,114,119,142],"low":[73],"ASR":[74,206],"due":[75],"inter-modal":[77],"semantic":[78],"inconsistency":[79],"from":[80],"insufficient":[81],"cross-modal":[82,147],"interaction.":[83],"other":[86],"dilemma":[89],"between":[90],"attack":[91,111,177,201],"effectiveness":[92,170],"stealthiness":[94],"limits":[95],"practical":[97],"applicability":[98],"of":[99,137,186,207],"texts.":[101],"To":[102],"address":[103],"these":[104],"issues,":[105],"we":[106],"propose":[107],"GIGAS,":[108],"innovative":[110],"uses":[113],"generative":[115,143],"explore":[118],"interaction":[120],"through":[121],"three":[122],"modules":[124],"tailored":[125],"solve":[127],"above-mentioned":[128],"problems.":[129],"MIGA":[130],"aligns":[131],"features":[134],"with":[135,157,203],"semantics":[136],"misleading":[138],"generated":[140],"mitigate":[146],"inconsistencies.":[148],"GSA":[149],"employs":[150],"MLLMs":[151],"generate":[153],"natural":[154],"texts":[156],"greater":[158],"variation":[159],"evaluate":[161],"similarity":[162],"filter":[164],"based":[165,179],"clean":[167],"images,":[168],"balancing":[169],"stealthiness.":[172],"Iteration":[173],"Allocation":[174],"dynamically":[175],"adjusts":[176],"iterations":[178],"image-text":[181],"similarity,":[182],"maximizing":[183],"utility":[185],"limited":[188],"iterations.":[189],"Experiments":[190],"conducted":[191],"various":[193],"VL":[194],"datasets":[198],"demonstrate":[199],"superior":[200],"performance,":[202],"average":[205],"89.09%":[208],"VQAv2.0.":[210],"Furthermore,":[211],"our":[212],"GIGAS":[213],"exhibits":[214],"outstanding":[215],"transferability,":[216],"around":[217],"60%":[218],"ASR,":[219],"across":[220],"diverse":[221],"specific":[224],"domains.":[225],"Our":[226],"code":[227],"will":[228],"be":[229],"available":[230],"at:":[231],"https://github.com/Yvonna-cloud/GIGAS.":[232]},"counts_by_year":[],"updated_date":"2026-06-07T06:13:29.825681","created_date":"2026-02-13T00:00:00"}