{"id":"https://openalex.org/W4416149692","doi":"https://doi.org/10.48550/arxiv.2502.19672","title":"Improving Adversarial Transferability in MLLMs via Dynamic Vision-Language Alignment Attack","display_name":"Improving Adversarial Transferability in MLLMs via Dynamic Vision-Language Alignment Attack","publication_year":2025,"publication_date":"2025-02-27","ids":{"openalex":"https://openalex.org/W4416149692","doi":"https://doi.org/10.48550/arxiv.2502.19672"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2502.19672","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.19672","pdf_url":"https://arxiv.org/pdf/2502.19672","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.19672","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Gu, Chenhe","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gu, Chenhe","raw_affiliation_strings":["University of California , Irvine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Irvine","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055994909","display_name":"Jindong Gu","orcid":"https://orcid.org/0009-0000-0574-0129","observed_orcids":["https://orcid.org/0009-0000-0574-0129"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Jindong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108885369","display_name":"Andong Hua","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hua, Andong","raw_affiliation_strings":["University of California , Santa Barbara"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Santa Barbara","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101601675","display_name":"Yao Qin","orcid":"https://orcid.org/0000-0002-1304-9933","observed_orcids":["https://orcid.org/0000-0002-1304-9933"]},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qin, Yao","raw_affiliation_strings":["University of California , Santa Barbara"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Santa Barbara","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9994999766349792,"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":0.9994999766349792,"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/T12357","display_name":"Digital Media Forensic Detection","score":9.999999747378752e-05,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0,"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/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9679999947547913},{"id":"https://openalex.org/keywords/adversarial-attacks","display_name":"adversarial attacks","score":0.9269999861717224},{"id":"https://openalex.org/keywords/adversarial-transferability","display_name":"adversarial transferability","score":0.8560000061988831},{"id":"https://openalex.org/keywords/vision-language-alignment","display_name":"vision-language alignment","score":0.8629999756813049},{"id":"https://openalex.org/keywords/targeted-attacks","display_name":"targeted attacks","score":0.8040000200271606},{"id":"https://openalex.org/keywords/dynamic-disturbances","display_name":"dynamic disturbances","score":0.7860000133514404},{"id":"https://openalex.org/keywords/adversarial-examples","display_name":"adversarial examples","score":0.7480000257492065}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.916700005531311},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.892300009727478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7357000112533569},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6062999963760376},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.555400013923645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5105000138282776},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4713999927043915},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39750000834465027},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29339998960494995},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2563999891281128}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2502.19672","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.19672","pdf_url":"https://arxiv.org/pdf/2502.19672","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2502.19672","doi":"https://doi.org/10.48550/arxiv.2502.19672","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.19672","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.19672","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.19672","pdf_url":"https://arxiv.org/pdf/2502.19672","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416149692.pdf","grobid_xml":"https://content.openalex.org/works/W4416149692.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1673923490","https://openalex.org/W1945616565","https://openalex.org/W2408141691","https://openalex.org/W2570685808","https://openalex.org/W2612637113","https://openalex.org/W2640329709","https://openalex.org/W4229005866","https://openalex.org/W4322718191","https://openalex.org/W4361194507","https://openalex.org/W4366850747","https://openalex.org/W4384918448","https://openalex.org/W4386185600","https://openalex.org/W4386977422","https://openalex.org/W4387994756","https://openalex.org/W4389116640","https://openalex.org/W4391157527","https://openalex.org/W4392181813","https://openalex.org/W4392934624","https://openalex.org/W4401306886","https://openalex.org/W4405467128","https://openalex.org/W4405595839","https://openalex.org/W4415538021","https://openalex.org/W7170083095"],"related_works":["https://openalex.org/W7126029536","https://openalex.org/W4402288734","https://openalex.org/W4415538021","https://openalex.org/W4408083564","https://openalex.org/W4408313304","https://openalex.org/W7163410934","https://openalex.org/W4407569771","https://openalex.org/W7134059898","https://openalex.org/W7117309717","https://openalex.org/W7134040424"],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs),":[4],"built":[5],"upon":[6],"LLMs,":[7],"have":[8],"recently":[9],"gained":[10],"attention":[11],"for":[12],"their":[13],"capabilities":[14],"in":[15],"image":[16],"recognition":[17],"and":[18,113],"understanding.":[19],"However,":[20],"while":[21],"MLLMs":[22],"are":[23],"vulnerable":[24],"to":[25,82],"adversarial":[26,103],"attacks,":[27],"the":[28,53,65,79,100],"transferability":[29,101],"of":[30,56,89,102],"these":[31],"attacks":[32],"across":[33,85,105],"different":[34,90],"models":[35,115],"remains":[36],"limited,":[37],"especially":[38],"under":[39],"targeted":[40],"attack":[41],"setting.":[42],"Existing":[43],"methods":[44],"primarily":[45],"focus":[46],"on":[47],"vision-specific":[48],"perturbations":[49,77],"but":[50],"struggle":[51],"with":[52],"complex":[54],"nature":[55],"vision-language":[57,80,87],"modality":[58],"alignment.":[59],"In":[60],"this":[61],"work,":[62],"we":[63],"introduce":[64],"Dynamic":[66],"Vision-Language":[67],"Alignment":[68],"(DynVLA)":[69],"Attack,":[70],"a":[71],"novel":[72],"approach":[73],"that":[74,96],"injects":[75],"dynamic":[76],"into":[78],"connector":[81],"enhance":[83],"generalization":[84],"diverse":[86],"alignment":[88],"models.":[91],"Our":[92],"experimental":[93],"results":[94],"show":[95],"DynVLA":[97],"significantly":[98],"improves":[99],"examples":[104],"various":[106],"MLLMs,":[107],"including":[108],"BLIP2,":[109],"InstructBLIP,":[110],"MiniGPT4,":[111],"LLaVA,":[112],"closed-source":[114],"such":[116],"as":[117],"Gemini.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}