{"id":"https://openalex.org/W4411472283","doi":"https://doi.org/10.1109/tmm.2025.3581811","title":"Exploring Transferability of Multimodal Adversarial Samples for Vision-Language Pre-Training Models With Contrastive Learning","display_name":"Exploring Transferability of Multimodal Adversarial Samples for Vision-Language Pre-Training Models With Contrastive Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411472283","doi":"https://doi.org/10.1109/tmm.2025.3581811"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3581811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3581811","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5035229016","display_name":"Youze Wang","orcid":"https://orcid.org/0009-0003-5621-6310"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Youze Wang","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058191990","display_name":"Wenbo Hu","orcid":"https://orcid.org/0000-0002-0639-2012"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbo Hu","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068755794","display_name":"Yinpeng Dong","orcid":"https://orcid.org/0000-0003-1299-683X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinpeng Dong","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042324027","display_name":"Hanwang Zhang","orcid":"https://orcid.org/0000-0001-7374-8739"},"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":"Hanwang Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341885","display_name":"Hang Su","orcid":"https://orcid.org/0000-0001-8294-6315"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Su","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051332325","display_name":"Richang Hong","orcid":"https://orcid.org/0000-0001-5461-3986"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Richang Hong","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5035229016"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":9.4273,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.97567507,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"27","issue":null,"first_page":"6410","last_page":"6421"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9603999853134155,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9603999853134155,"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/T12151","display_name":"Interpreting and Communication in Healthcare","score":0.9333000183105469,"subfield":{"id":"https://openalex.org/subfields/3600","display_name":"General Health Professions"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8586523532867432},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7627612352371216},{"id":"https://openalex.org/keywords/transferability","display_name":"Transferability","score":0.7216955423355103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6301587820053101},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6107892990112305},{"id":"https://openalex.org/keywords/contrastive-analysis","display_name":"Contrastive analysis","score":0.5683028101921082},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3871765434741974},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33260780572891235},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20306998491287231}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8586523532867432},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7627612352371216},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.7216955423355103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6301587820053101},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6107892990112305},{"id":"https://openalex.org/C2777629044","wikidata":"https://www.wikidata.org/wiki/Q614959","display_name":"Contrastive analysis","level":2,"score":0.5683028101921082},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3871765434741974},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33260780572891235},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20306998491287231},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3581811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3581811","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2711818151","display_name":null,"funder_award_id":"62306098","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5586753922","display_name":null,"funder_award_id":"U23B2031","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8794727857","display_name":null,"funder_award_id":"MMC202412","funder_id":"https://openalex.org/F4320321435","funder_display_name":"Anhui University"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321435","display_name":"Anhui University","ror":"https://ror.org/05th6yx34"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W2774644650","https://openalex.org/W2905526464","https://openalex.org/W2962847335","https://openalex.org/W2962858109","https://openalex.org/W2969542116","https://openalex.org/W2996851481","https://openalex.org/W3038033387","https://openalex.org/W3101449015","https://openalex.org/W3158360872","https://openalex.org/W3161469108","https://openalex.org/W3171288285","https://openalex.org/W3180181113","https://openalex.org/W3183199078","https://openalex.org/W3186991201","https://openalex.org/W3212790025","https://openalex.org/W4214703392","https://openalex.org/W4214764354","https://openalex.org/W4225166070","https://openalex.org/W4283317927","https://openalex.org/W4293846201","https://openalex.org/W4304701424","https://openalex.org/W4312877428","https://openalex.org/W4386065512","https://openalex.org/W4386736875","https://openalex.org/W4389988150","https://openalex.org/W4390889737","https://openalex.org/W4400074770"],"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":{"The":[0],"integration":[1],"of":[2,22,29,58,87],"visual":[3,94],"and":[4,71,79,93,118],"textual":[5],"data":[6],"in":[7,26,62,101],"Vision-Language":[8],"Pre-training":[9],"(VLP)":[10],"models":[11],"is":[12],"crucial":[13],"for":[14],"enhancing":[15],"vision-language":[16],"understanding.":[17],"However,":[18],"the":[19,27,56,85],"adversarial":[20,47,60,69,115,121],"robustness":[21],"these":[23],"models,":[24],"especially":[25],"alignment":[28],"image-text":[30,78,91],"features,":[31],"has":[32],"not":[33],"yet":[34],"been":[35],"sufficiently":[36],"explored.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"introduce":[42],"a":[43,102,108],"novel":[44],"gradient-based":[45],"multimodal":[46,59,120],"attack":[48,116,122],"method,":[49],"underpinned":[50],"by":[51],"contrastive":[52,81],"learning,":[53],"to":[54],"improve":[55],"transferability":[57],"samples":[61],"VLP":[63],"models.":[64],"This":[65],"method":[66],"concurrently":[67],"generates":[68],"texts":[70],"images":[72],"within":[73],"imperceptive":[74],"perturbation,":[75],"employing":[76],"both":[77],"intra-modal":[80],"loss.":[82],"We":[83],"evaluate":[84],"effectiveness":[86],"our":[88],"approach":[89],"on":[90],"retrieval":[92],"entailment":[95],"tasks,":[96],"using":[97],"publicly":[98],"available":[99],"datasets":[100],"black-box":[103],"setting.":[104],"Extensive":[105],"experiments":[106],"indicate":[107],"significant":[109],"advancement":[110],"over":[111],"existing":[112],"single-modal":[113],"transfer-based":[114],"methods":[117],"current":[119],"approaches.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
