{"id":"https://openalex.org/W4414059377","doi":"https://doi.org/10.1007/s40747-025-02036-y","title":"JDA-attack: leveraging joint multimodal data augmentation to enhance adversarial transferability of vision-language pre-training models","display_name":"JDA-attack: leveraging joint multimodal data augmentation to enhance adversarial transferability of vision-language pre-training models","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W4414059377","doi":"https://doi.org/10.1007/s40747-025-02036-y"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-025-02036-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-02036-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-02036-y.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex &amp; Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-02036-y.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111319008","display_name":"Xujie Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xujie Ren","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, 710072, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, 710072, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000152062","display_name":"Caikun Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101382","display_name":"People's Liberation Army No. 150 Hospital","ror":"https://ror.org/014nsap67","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210101382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Caikun Zhang","raw_affiliation_strings":["Unit 63892 of People\u2019s Liberation Army of China, Luoyang, 471003, Henan, China"],"affiliations":[{"raw_affiliation_string":"Unit 63892 of People\u2019s Liberation Army of China, Luoyang, 471003, Henan, China","institution_ids":["https://openalex.org/I4210101382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103175439","display_name":"Guoqiang Han","orcid":"https://orcid.org/0000-0001-5265-9112"},"institutions":[{"id":"https://openalex.org/I4210101382","display_name":"People's Liberation Army No. 150 Hospital","ror":"https://ror.org/014nsap67","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210101382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqiang Han","raw_affiliation_strings":["Unit 63892 of People\u2019s Liberation Army of China, Luoyang, 471003, Henan, China"],"affiliations":[{"raw_affiliation_string":"Unit 63892 of People\u2019s Liberation Army of China, Luoyang, 471003, Henan, China","institution_ids":["https://openalex.org/I4210101382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427335","display_name":"Bin Chen","orcid":"https://orcid.org/0000-0002-3979-021X"},"institutions":[{"id":"https://openalex.org/I4210106098","display_name":"Hospital 463 People's Liberation Army","ror":"https://ror.org/01mmm4p44","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210106098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Chen","raw_affiliation_strings":["Unit 93212 of People\u2019s Liberation Army of China, Dalian, 116000, Liaoning, China"],"affiliations":[{"raw_affiliation_string":"Unit 93212 of People\u2019s Liberation Army of China, Dalian, 116000, Liaoning, China","institution_ids":["https://openalex.org/I4210106098"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100574529","display_name":"Zepeng Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zepeng Fan","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, 710072, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, 710072, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5111319008"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12822795,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"10","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":0.9998000264167786,"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":0.9998000264167786,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9980000257492065,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976999759674072,"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":0.6985999941825867},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5504000186920166},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5299000144004822},{"id":"https://openalex.org/keywords/transferability","display_name":"Transferability","score":0.5271999835968018},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4713999927043915},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.46650001406669617},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4278999865055084},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.40720000863075256}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7918999791145325},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6985999941825867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.602400004863739},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5504000186920166},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5299000144004822},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.5271999835968018},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4733999967575073},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4713999927043915},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.46650001406669617},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4278999865055084},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.37450000643730164},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2680000066757202},{"id":"https://openalex.org/C171836373","wikidata":"https://www.wikidata.org/wiki/Q2266329","display_name":"Linear interpolation","level":3,"score":0.2630999982357025},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.257999986410141},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-025-02036-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-02036-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-02036-y.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex &amp; Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:47ea51eb7d364d3d8e5d7bcfbd703afa","is_oa":true,"landing_page_url":"https://doaj.org/article/47ea51eb7d364d3d8e5d7bcfbd703afa","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complex & Intelligent Systems, Vol 11, Iss 10, Pp 1-16 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-025-02036-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-02036-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-02036-y.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex &amp; Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414059377.pdf","grobid_xml":"https://content.openalex.org/works/W4414059377.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W2489434015","https://openalex.org/W2774644650","https://openalex.org/W2962847335","https://openalex.org/W2963542245","https://openalex.org/W2963857521","https://openalex.org/W2971296908","https://openalex.org/W2991496458","https://openalex.org/W3034176567","https://openalex.org/W3101449015","https://openalex.org/W3127807678","https://openalex.org/W3153469116","https://openalex.org/W3158360872","https://openalex.org/W3171288285","https://openalex.org/W3206020652","https://openalex.org/W4225832925","https://openalex.org/W4283075937","https://openalex.org/W4283317927","https://openalex.org/W4285115684","https://openalex.org/W4294310809","https://openalex.org/W4312877428","https://openalex.org/W4366817438","https://openalex.org/W4387967929","https://openalex.org/W4390116303","https://openalex.org/W4390871946","https://openalex.org/W4390889737","https://openalex.org/W4392172801","https://openalex.org/W4399198213","https://openalex.org/W4400524868","https://openalex.org/W4400859766","https://openalex.org/W4401024758","https://openalex.org/W4402288734","https://openalex.org/W4403791218","https://openalex.org/W4411472283"],"related_works":["https://openalex.org/W4288055406","https://openalex.org/W4200630034","https://openalex.org/W3137894200","https://openalex.org/W3092178728","https://openalex.org/W4226402597","https://openalex.org/W3132910851","https://openalex.org/W4377864639","https://openalex.org/W4409346678","https://openalex.org/W4392340763","https://openalex.org/W4283325551"],"abstract_inverted_index":{"Visual-Language":[0],"Pre-training":[1],"(VLP)":[2],"Models":[3],"demonstrate":[4,181],"exceptional":[5],"capability":[6],"in":[7,30,37,105],"understanding":[8],"the":[9,71,103,106,127,158,167],"interactions":[10],"between":[11,161],"images":[12,76,142],"and":[13,46,55,77,143,178],"text,":[14],"yet":[15],"they":[16],"remain":[17],"vulnerable":[18],"to":[19,58,79,152],"multimodal":[20,34,117,135,170],"adversarial":[21,24,35,131,171],"examples.":[22,172],"Investigating":[23],"attacks":[25],"against":[26],"VLP":[27,66,179],"models,":[28],"particularly":[29],"generating":[31],"highly":[32],"transferable":[33],"examples":[36],"black-box":[38],"settings,":[39],"is":[40,150],"crucial":[41],"for":[42],"developing":[43],"more":[44],"robust":[45],"practical":[47],"models.":[48],"Current":[49],"research":[50],"typically":[51],"leverages":[52],"modality":[53,95],"interaction":[54],"data":[56,89,118,154],"diversity":[57,155],"enhance":[59,153],"attack":[60,121,187],"transferability.":[61,188],"However,":[62],"unlike":[63],"unimodal":[64,88],"learning,":[65],"models":[67,180],"heavily":[68],"rely":[69],"on":[70,93,175],"feature":[72],"learning":[73],"of":[74,130,141,145,169],"both":[75],"text":[78,147],"accurately":[80],"align":[81],"semantics":[82],"across":[83],"different":[84],"modalities.":[85],"Directly":[86],"applying":[87],"augmentation":[90,137],"methods":[91],"independently":[92],"each":[94],"may":[96],"disrupt":[97],"inter-modal":[98],"semantic":[99,159],"matching,":[100],"thus":[101,164],"leading":[102],"perturbations":[104],"wrong":[107],"direction.":[108],"To":[109],"address":[110],"this":[111],"challenge,":[112],"we":[113,133],"propose":[114],"a":[115],"joint":[116],"augmentation-based":[119],"transfer":[120],"method,":[122],"termed":[123],"JDA-Attack.":[124],"Specifically,":[125],"during":[126],"iterative":[128],"generation":[129],"examples,":[132],"perform":[134],"collaborative":[136],"through":[138],"linear":[139],"interpolation":[140],"concatenation":[144],"corresponding":[146],"sequences.":[148],"It":[149],"able":[151],"while":[156],"preserving":[157],"relationships":[160],"image-text":[162],"pairs,":[163],"effectively":[165],"improving":[166],"transferability":[168],"Extensive":[173],"experiments":[174],"various":[176],"datasets":[177],"that":[182],"our":[183],"method":[184],"achieves":[185],"superior":[186]},"counts_by_year":[],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}
