{"id":"https://openalex.org/W7138276614","doi":"https://doi.org/10.1609/aaai.v40i5.37388","title":"Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimization","display_name":"Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimization","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138276614","doi":"https://doi.org/10.1609/aaai.v40i5.37388"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i5.37388","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37388","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37388/41350","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/37388/41350","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129649664","display_name":"Xiang Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Fang","raw_affiliation_strings":["School of Software Engineering, Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113067511","display_name":"Wanlong Fang","orcid":"https://orcid.org/0000-0003-4480-3107"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wanlong Fang","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129748655","display_name":"Changshuo Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Changshuo Wang","raw_affiliation_strings":["University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"5","first_page":"3867","last_page":"3875"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7516999840736389,"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":0.7516999840736389,"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":0.12120000272989273,"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":0.04309999942779541,"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":0.8531000018119812},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5737000107765198},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5252000093460083},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.4528000056743622},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.44279998540878296},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4399999976158142},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.43529999256134033},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.40799999237060547}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8531000018119812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7293000221252441},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5737000107765198},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5252000093460083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5121999979019165},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.4528000056743622},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.44279998540878296},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4399999976158142},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.43529999256134033},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.4025999903678894},{"id":"https://openalex.org/C80191262","wikidata":"https://www.wikidata.org/wiki/Q5477668","display_name":"Fragility","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33660000562667847},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33160001039505005},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33009999990463257},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i5.37388","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37388","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37388/41350","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/37388","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37388","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.v40i5.37388","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37388","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37388/41350","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":[{"display_name":"Peace, Justice and strong institutions","score":0.5264755487442017,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138276614.pdf","grobid_xml":"https://content.openalex.org/works/W7138276614.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Vision-Language":[1],"Models":[2],"(LVLMs)":[3],"have":[4],"transformed":[5],"multi-modal":[6,77],"understanding,":[7],"excelling":[8],"in":[9,133],"tasks":[10,163,188],"like":[11,40],"image":[12,107],"captioning":[13],"and":[14,21,43,93,120,160,164],"visual":[15,20,124],"question":[16],"answering":[17],"by":[18,110,130],"integrating":[19],"textual":[22],"inputs.":[23,125],"However,":[24],"their":[25,58,157],"robustness":[26,121],"against":[27,79],"adversarial":[28,175],"attacks\u2014particularly":[29],"those":[30],"exploiting":[31],"both":[32],"modalities\u2014remains":[33],"underexplored,":[34],"posing":[35],"risks":[36],"to":[37,117,170],"critical":[38],"applications":[39],"autonomous":[41],"driving":[42],"content":[44],"moderation.":[45],"Existing":[46],"attacks":[47,78],"focus":[48],"on":[49,189],"single":[50],"modalities":[51],"or":[52],"require":[53],"impractical":[54],"white-box":[55],"access,":[56],"limiting":[57],"real-world":[59],"relevance.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64],"introduce":[65],"Multi-Modal":[66],"Adversarial":[67,88],"Synergy":[68],"(MMAS),":[69],"a":[70,84,94,144,185],"groundbreaking":[71],"framework":[72],"that":[73],"crafts":[74],"universal,":[75],"black-box":[76],"LVLMs.":[80],"MMAS":[81],"simultaneously":[82],"generates":[83],"texture":[85,115],"scale-constrained":[86],"Universal":[87],"Perturbation":[89],"(UAP)":[90],"for":[91,98],"images":[92],"learnable":[95],"prompt":[96],"perturbation":[97],"text,":[99],"optimized":[100],"jointly":[101],"using":[102],"only":[103],"model":[104,201],"queries.":[105],"The":[106,126],"perturbation,":[108,128],"bounded":[109],"an":[111,131],"L\u221e-norm,":[112],"leverages":[113],"wavelet-based":[114],"constraints":[116],"ensure":[118],"imperceptibility":[119],"across":[122,162],"diverse":[123],"text":[127],"constrained":[129],"L2-norm":[132],"the":[134,152,172,197,200],"embedding":[135],"space,":[136],"maintains":[137],"semantic":[138],"coherence":[139],"while":[140],"steering":[141],"outputs":[142],"toward":[143],"target.":[145],"A":[146],"novel":[147],"cross-modal":[148],"regularization":[149],"term":[150],"aligns":[151],"perturbations\u2019":[153],"gradient":[154],"directions,":[155],"enhancing":[156],"synergistic":[158],"impact":[159],"transferability":[161],"models.":[165],"Extensive":[166],"experiments":[167],"are":[168],"conducted":[169],"verify":[171],"strong":[173],"universal":[174],"capabilities":[176],"of":[177,187,199],"our":[178],"proposed":[179],"attack":[180],"with":[181],"prevalent":[182],"LVLMs,":[183],"spanning":[184],"spectrum":[186],"various":[190],"datasets,":[191],"all":[192],"achieved":[193],"without":[194],"delving":[195],"into":[196],"details":[198],"structures.":[202]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}