{"id":"https://openalex.org/W7138093231","doi":"https://doi.org/10.1609/aaai.v40i7.37420","title":"Transferability of Adversarial Attacks in Video-based MLLMs: A Cross-modal Image-to-Video Approach","display_name":"Transferability of Adversarial Attacks in Video-based MLLMs: A Cross-modal Image-to-Video Approach","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138093231","doi":"https://doi.org/10.1609/aaai.v40i7.37420"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i7.37420","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37420","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37420/41382","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37420/41382","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129656844","display_name":"Linhao Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Linhao Huang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University\nPeng Cheng Laboratory, Shenzhen, Guangdong, China\nSouthern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University\nPeng Cheng Laboratory, Shenzhen, Guangdong, China\nSouthern University of Science and Technology","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I3045169105","https://openalex.org/I3131625388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129708685","display_name":"Xue Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xue Jiang","raw_affiliation_strings":["Southern University of Science and Technology\nTMLR Group, Hong Kong Baptist University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology\nTMLR Group, Hong Kong Baptist University","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129659861","display_name":"Zhiqiang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhiqiang Wang","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129685287","display_name":"Wentao Mo","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wentao Mo","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University\nSouthern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University\nSouthern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129745596","display_name":"Xi Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Xiao","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University\nPeng Cheng Laboratory, Shenzhen, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University\nPeng Cheng Laboratory, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I3131625388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129677931","display_name":"Yong-Jie Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104233","display_name":"China Electronics Corporation (China)","ror":"https://ror.org/00vsv8c52","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210104233"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong-Jie Yin","raw_affiliation_strings":["China Electronics Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Electronics Corporation","institution_ids":["https://openalex.org/I4210104233"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129642879","display_name":"Bo Han","orcid":null},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bo Han","raw_affiliation_strings":["TMLR Group, Hong Kong Baptist University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TMLR Group, Hong Kong Baptist University","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129732890","display_name":"Feng Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zheng","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5129656844"],"corresponding_institution_ids":["https://openalex.org/I3045169105","https://openalex.org/I3131625388","https://openalex.org/I4210136793"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28482528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"7","first_page":"5067","last_page":"5075"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9760000109672546,"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"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9760000109672546,"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":0.00860000029206276,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.0017999999690800905,"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/adversarial-system","display_name":"Adversarial system","score":0.9438999891281128},{"id":"https://openalex.org/keywords/transferability","display_name":"Transferability","score":0.791700005531311},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5081999897956848},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.42969998717308044},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.37540000677108765},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.34950000047683716},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3450999855995178}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9438999891281128},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.791700005531311},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7771999835968018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5867000222206116},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5081999897956848},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5005000233650208},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.34950000047683716},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.2632000148296356},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i7.37420","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37420","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37420/41382","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"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i7.37420","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37420","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37420/41382","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":[],"awards":[{"id":"https://openalex.org/G4392973527","display_name":null,"funder_award_id":"62376235","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7957291013","display_name":null,"funder_award_id":"2022A1515011652","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138093231.pdf","grobid_xml":"https://content.openalex.org/works/W7138093231.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video-based":[0],"multimodal":[1,14,89,118,184],"large":[2,119],"language":[3,120],"models":[4],"(V-MLLMs)":[5],"have":[6],"shown":[7],"vulnerability":[8],"to":[9,22,67,87,127,139,157,187],"adversarial":[10,20,42,51,129,148,172],"examples":[11,173],"in":[12,59,74,102],"video-text":[13,183],"tasks.":[15,185],"However,":[16],"the":[17,39,68,97,107,144],"transferability":[18,40,177],"of":[19,41,99,211],"videos":[21],"unseen":[23],"models\u2014a":[24],"common":[25],"and":[26,84,95,134,215],"practical":[27],"real-world":[28],"scenario\u2014remains":[29],"unexplored.":[30],"In":[31,112],"this":[32],"paper,":[33],"we":[34,65,105,114],"pioneer":[35],"an":[36,116],"investigation":[37],"into":[38],"video":[43,76,130,141],"samples":[44],"across":[45,178],"V-MLLMs.":[46],"We":[47],"find":[48],"that":[49,167,174],"existing":[50],"attack":[52,207],"methods":[53],"face":[54],"significant":[55],"limitations":[56,94],"when":[57],"applied":[58],"black-box":[60,103,194],"settings":[61],"for":[62,219],"V-MLLMs,":[63],"which":[64],"attribute":[66],"following":[69],"shortcomings:":[70],"(1)":[71],"lacking":[72],"generalization":[73],"perturbing":[75],"features,":[77],"(2)":[78],"focusing":[79],"only":[80],"on":[81,181,190,213,217],"sparse":[82],"key-frames,":[83],"(3)":[85],"failing":[86],"integrate":[88],"information.":[90],"To":[91],"address":[92],"these":[93,191],"deepen":[96],"understanding":[98],"V-MLLM":[100],"vulnerabilities":[101],"scenarios,":[104],"introduce":[106],"Image-to-Video":[108],"MLLM":[109],"(I2V-MLLM)":[110],"attack.":[111],"I2V-MLLM,":[113],"utilize":[115],"image-based":[117],"model":[121,126],"(I-MLLM)":[122],"as":[123,198],"a":[124,151,199],"surrogate":[125,200],"craft":[128],"samples.":[131],"Multimodal":[132],"interactions":[133],"spatiotemporal":[135],"information":[136],"are":[137],"integrated":[138],"disrupt":[140],"representations":[142],"within":[143],"latent":[145],"space,":[146],"improving":[147],"transferability.":[149],"Additionally,":[150],"perturbation":[152],"propagation":[153],"technique":[154],"is":[155],"introduced":[156],"handle":[158],"different":[159,179],"unknown":[160],"frame":[161],"sampling":[162],"strategies.":[163],"Experimental":[164],"results":[165],"demonstrate":[166],"our":[168,193],"method":[169],"can":[170],"generate":[171],"exhibit":[175],"strong":[176],"V-MLLMs":[180],"multiple":[182],"Compared":[186],"white-box":[188],"attacks":[189,195],"models,":[192],"(using":[196],"BLIP-2":[197],"model)":[201],"achieve":[202],"competitive":[203],"performance,":[204],"with":[205],"average":[206],"success":[208],"rate":[209],"(AASR)":[210],"57.98%":[212],"MSVD-QA":[214],"58.26%":[216],"MSRVTT-QA":[218],"Zero-Shot":[220],"VideoQA":[221],"tasks,":[222],"respectively.":[223]},"counts_by_year":[],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2026-03-18T00:00:00"}