{"id":"https://openalex.org/W4410852834","doi":"https://doi.org/10.1109/tifs.2025.3574976","title":"Modality-Specific Interactive Attack for Vision-Language Pre-Training Models","display_name":"Modality-Specific Interactive Attack for Vision-Language Pre-Training Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4410852834","doi":"https://doi.org/10.1109/tifs.2025.3574976"},"language":"en","primary_location":{"id":"doi:10.1109/tifs.2025.3574976","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2025.3574976","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"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 Information Forensics and Security","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ink.library.smu.edu.sg/sis_research/10240","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101937611","display_name":"Haiqi Zhang","orcid":"https://orcid.org/0000-0002-2617-9665"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haiqi Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005624589","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-6973-8121"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hao Tang","raw_affiliation_strings":["Centre for Smart Health, The Hong Kong Polytechnic University, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Centre for Smart Health, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101812029","display_name":"Yanpeng Sun","orcid":"https://orcid.org/0000-0001-6249-5596"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanpeng Sun","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056103024","display_name":"Shengfeng He","orcid":"https://orcid.org/0000-0002-3802-4644"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shengfeng He","raw_affiliation_strings":["School of Computing and Information Systems, Singapore Management University, Bras Basah, Singapore","School of Computing and Information Systems, Singapore Management University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, Singapore Management University, Bras Basah, Singapore","institution_ids":["https://openalex.org/I79891267"]},{"raw_affiliation_string":"School of Computing and Information Systems, Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017096005","display_name":"Zechao Li","orcid":"https://orcid.org/0000-0002-5341-5985"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zechao Li","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101937611"],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":44.7799,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.99773104,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"20","issue":null,"first_page":"5663","last_page":"5677"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9578999876976013,"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":0.9578999876976013,"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/T10028","display_name":"Topic Modeling","score":0.9376999735832214,"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/computer-science","display_name":"Computer science","score":0.8210259079933167},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7245039939880371},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4918217658996582},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4867732524871826},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.398738831281662},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3894807696342468},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.38233670592308044},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3745889365673065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8210259079933167},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7245039939880371},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4918217658996582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4867732524871826},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.398738831281662},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3894807696342468},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.38233670592308044},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3745889365673065},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tifs.2025.3574976","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2025.3574976","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"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 Information Forensics and Security","raw_type":"journal-article"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-11240","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/10240","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/TIFS.2025.3574976","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-11240","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/10240","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/TIFS.2025.3574976","raw_type":"Journal Article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2531279109","display_name":null,"funder_award_id":"62425603","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6750246608","display_name":null,"funder_award_id":"BK20240011","funder_id":"https://openalex.org/F4320334982","funder_display_name":"Basic Research Program of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334982","display_name":"Basic Research Program of Jiangsu Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2774644650","https://openalex.org/W2832876791","https://openalex.org/W2905526464","https://openalex.org/W2946086442","https://openalex.org/W2962847335","https://openalex.org/W2964345792","https://openalex.org/W2978078758","https://openalex.org/W3015646845","https://openalex.org/W3033235266","https://openalex.org/W3080270960","https://openalex.org/W3091588028","https://openalex.org/W3101449015","https://openalex.org/W3121523901","https://openalex.org/W3173220247","https://openalex.org/W3186991201","https://openalex.org/W3214910576","https://openalex.org/W4214764354","https://openalex.org/W4214870408","https://openalex.org/W4225166070","https://openalex.org/W4225832925","https://openalex.org/W4280538209","https://openalex.org/W4283317927","https://openalex.org/W4293846201","https://openalex.org/W4294409011","https://openalex.org/W4312777424","https://openalex.org/W4312820932","https://openalex.org/W4312877428","https://openalex.org/W4313064375","https://openalex.org/W4318960928","https://openalex.org/W4321021543","https://openalex.org/W4365420523","https://openalex.org/W4378976956","https://openalex.org/W4382657968","https://openalex.org/W4385764993","https://openalex.org/W4385767419","https://openalex.org/W4386065627","https://openalex.org/W4386066385","https://openalex.org/W4386075498","https://openalex.org/W4386076150","https://openalex.org/W4386162736","https://openalex.org/W4387967929","https://openalex.org/W4390097598","https://openalex.org/W4390604007","https://openalex.org/W4390871747","https://openalex.org/W4390889737","https://openalex.org/W4401508445","https://openalex.org/W4402302904","https://openalex.org/W4402959346","https://openalex.org/W4405056285","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6734194636","https://openalex.org/W6752876022","https://openalex.org/W6767513282","https://openalex.org/W6768366551","https://openalex.org/W6791353385","https://openalex.org/W6795475546","https://openalex.org/W6798805250","https://openalex.org/W6803084059","https://openalex.org/W6803435029","https://openalex.org/W6811013733","https://openalex.org/W6838510352","https://openalex.org/W6852839128","https://openalex.org/W6856800273","https://openalex.org/W6856963872","https://openalex.org/W6859228745","https://openalex.org/W6859289544"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"have":[2],"heightened":[3],"the":[4,7,43,81,129,137,144,157,176,188,195,211],"interest":[5],"in":[6,117],"adversarial":[8,160],"transferability":[9,96],"of":[10,26,84,159,173,197],"Vision-Language":[11],"Pre-training":[12],"(VLP)":[13],"models.":[14],"However,":[15],"most":[16],"existing":[17],"strategies":[18],"constrained":[19],"by":[20,87,97,140],"two":[21],"persistent":[22],"limitations:":[23],"suboptimal":[24],"utilization":[25],"cross-modal":[27],"interactive":[28],"information,":[29],"and":[30,124,154,192],"inherent":[31],"discrepancies":[32],"across":[33,101,151],"hierarchical":[34,152],"textual":[35],"representation.":[36],"To":[37],"address":[38],"these":[39],"challenges,":[40],"we":[41,71,111,135,163],"propose":[42],"Modality-Specific":[44],"Interactive":[45],"Attack":[46],"(MSI-Attack),":[47],"a":[48,113,205],"novel":[49],"approach":[50],"that":[51],"integrates":[52],"semantic-level":[53],"image":[54,68],"perturbations":[55,79,169],"with":[56,119,170],"embedding-level":[57],"text":[58,91,133],"perturbations,":[59],"all":[60,209],"while":[61],"maintaining":[62],"minimal":[63],"inter-modal":[64],"constraints.":[65],"In":[66],"our":[67],"attack":[69,178],"methodology,":[70],"introduce":[72],"Multi-modal":[73],"Integrated":[74],"Gradients":[75],"(MIG)":[76],"to":[77,127],"guide":[78],"toward":[80],"core":[82],"semantics":[83],"images,":[85],"enriched":[86],"their":[88],"associated":[89],"deeply":[90],"information.":[92],"This":[93,147],"technique":[94],"enhances":[95,156],"capturing":[98],"consistent":[99],"features":[100],"various":[102],"models,":[103],"thereby":[104],"effectively":[105],"misleading":[106],"similar-model":[107],"perception":[108],"areas.":[109],"Additionally,":[110],"employ":[112],"momentum":[114],"iteration":[115],"strategy":[116],"conjunction":[118],"MIG,":[120],"which":[121],"amalgamates":[122],"current":[123],"historical":[125],"gradients":[126],"expedite":[128],"perturbation":[130,138],"updates.":[131],"For":[132],"attacks,":[134],"streamline":[136],"process":[139],"operating":[141],"exclusively":[142],"at":[143],"embedding":[145],"level.":[146],"reduces":[148],"semantic":[149,168],"gaps":[150],"structures":[153],"significantly":[155],"generalizability":[158],"text.":[161],"Moreover,":[162],"delve":[164],"deeper":[165],"into":[166],"how":[167],"varying":[171],"degrees":[172],"similarity":[174],"affect":[175],"overall":[177],"effectiveness.":[179],"Our":[180,199],"experimental":[181],"results":[182],"on":[183],"image-text":[184],"retrieval":[185],"tasks":[186],"using":[187],"multi-modal":[189],"datasets":[190],"Flickr30K":[191],"MSCOCO":[193],"underscore":[194],"efficacy":[196],"MSI-Attack.":[198],"method":[200],"achieves":[201],"superior":[202],"performance,":[203],"setting":[204],"new":[206],"state-of-the-art":[207],"benchmark,":[208],"without":[210],"need":[212],"for":[213],"additional":[214],"mechanisms.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":12}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}