{"id":"https://openalex.org/W7125959518","doi":"https://doi.org/10.1109/tip.2026.3651982","title":"Individual and Common Attack: Enhancing Transferability in VLP Models Through Modal Feature Exploitation","display_name":"Individual and Common Attack: Enhancing Transferability in VLP Models Through Modal Feature Exploitation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7125959518","doi":"https://doi.org/10.1109/tip.2026.3651982","pmid":"https://pubmed.ncbi.nlm.nih.gov/41605159"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3651982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3651982","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5018343275","display_name":"Yaguan Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yaguan Qian","raw_affiliation_strings":["School of Artificial Intelligence and Information Engineering, Zhejiang University of Science and Technology, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Information Engineering, Zhejiang University of Science and Technology, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124139962","display_name":"Yaxin Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaxin Kong","raw_affiliation_strings":["School of Artificial Intelligence and Information Engineering, Zhejiang University of Science and Technology, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Information Engineering, Zhejiang University of Science and Technology, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qiqi Bao","orcid":"https://orcid.org/0009-0004-1703-6090"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiqi Bao","raw_affiliation_strings":["School of Artificial Intelligence and Information Engineering, Zhejiang University of Science and Technology, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Information Engineering, Zhejiang University of Science and Technology, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040547391","display_name":"Zhaoquan Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoquan Gu","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124057947","display_name":"Bin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Wang","raw_affiliation_strings":["Zhejiang Key Laboratory of Artificial Intelligence of Things (AIoT) Network and Data Security, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Key Laboratory of Artificial Intelligence of Things (AIoT) Network and Data Security, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124064565","display_name":"Shouling Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shouling Ji","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124132939","display_name":"Jianping Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111288","display_name":"Meta (United Kingdom)","ror":"https://ror.org/020ye1821","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210111288","https://openalex.org/I4210114444"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianping Zhang","raw_affiliation_strings":["Meta AI, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Meta AI, Hong Kong, China","institution_ids":["https://openalex.org/I4210111288"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124120822","display_name":"Zhen Lei","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Lei","raw_affiliation_strings":["Center for Biometrics and Security Research and the National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Biometrics and Security Research and the National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5018343275"],"corresponding_institution_ids":["https://openalex.org/I168879160"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2118284,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"1082","last_page":"1095"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.885200023651123,"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":0.885200023651123,"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":0.05339999869465828,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.010700000450015068,"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/overfitting","display_name":"Overfitting","score":0.8090999722480774},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.8040000200271606},{"id":"https://openalex.org/keywords/transferability","display_name":"Transferability","score":0.6358000040054321},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5807999968528748},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45680001378059387},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.45159998536109924},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4228000044822693},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4092000126838684}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8090999722480774},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8040000200271606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7368000149726868},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7195000052452087},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.6358000040054321},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6197999715805054},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5807999968528748},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45680001378059387},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.31540000438690186},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3001999855041504},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2784000039100647},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3651982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3651982","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:41605159","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41605159","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4835197925567627}],"awards":[{"id":"https://openalex.org/G207383538","display_name":null,"funder_award_id":"U23B2054","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2902468357","display_name":null,"funder_award_id":"62372137","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3170340769","display_name":null,"funder_award_id":"2024YFB3108100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G398690329","display_name":null,"funder_award_id":"62506399","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4930386054","display_name":null,"funder_award_id":"62472335","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5681569201","display_name":null,"funder_award_id":"2024yjskc19","funder_id":"https://openalex.org/F4320321223","funder_display_name":"Gyeongnam National University of Science and Technology"},{"id":"https://openalex.org/G6047521378","display_name":null,"funder_award_id":"62476250","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6475258168","display_name":null,"funder_award_id":"62506339","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321223","display_name":"Gyeongnam National University of Science and Technology","ror":"https://ror.org/059r50h13"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2194775991","https://openalex.org/W2489434015","https://openalex.org/W2506483933","https://openalex.org/W2803259101","https://openalex.org/W2952524542","https://openalex.org/W2960655175","https://openalex.org/W2962681491","https://openalex.org/W2962764817","https://openalex.org/W2969542116","https://openalex.org/W2996851481","https://openalex.org/W3035454331","https://openalex.org/W3101449015","https://openalex.org/W3106050153","https://openalex.org/W3171288285","https://openalex.org/W4225832925","https://openalex.org/W4283317927","https://openalex.org/W4293846201","https://openalex.org/W4312877428","https://openalex.org/W4313178921","https://openalex.org/W4385245566","https://openalex.org/W4386075546","https://openalex.org/W4386076150","https://openalex.org/W4387967929","https://openalex.org/W4390872450","https://openalex.org/W4390874153","https://openalex.org/W4390889737","https://openalex.org/W4391992568","https://openalex.org/W4393154081","https://openalex.org/W4393184763","https://openalex.org/W4400524868","https://openalex.org/W4400771068","https://openalex.org/W4402776440","https://openalex.org/W4402959346","https://openalex.org/W4403791752","https://openalex.org/W4404239148"],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Pretrained":[1],"(VLP)":[2],"models":[3],"exhibit":[4],"strong":[5],"multimodal":[6,182],"understanding":[7],"and":[8,20,68,104,124,179,206],"reasoning":[9],"capabilities,":[10],"finding":[11],"wide":[12],"application":[13],"in":[14,35,203],"tasks":[15],"such":[16],"as":[17,55],"image-text":[18],"retrieval":[19],"visual":[21],"grounding.":[22],"However,":[23],"they":[24],"remain":[25],"highly":[26],"vulnerable":[27],"to":[28,62,75,120,145,151,172],"adversarial":[29,42,60,81,87,147],"attacks,":[30],"posing":[31],"serious":[32],"reliability":[33],"concerns":[34],"safety-critical":[36],"scenarios.":[37,209],"We":[38],"observe":[39],"that":[40,64],"existing":[41],"examples":[43,61],"optimization":[44],"methods":[45],"typically":[46],"rely":[47],"on":[48],"individual":[49,99,115],"features":[50,100,106,116,131],"from":[51,149],"the":[52,58,78,127,137,140,152,156,162,184,195],"other":[53,157],"modality":[54,103,119],"guidance,":[56],"causing":[57],"crafted":[59],"overfit":[63],"modality's":[65],"learning":[66,153],"preferences":[67],"thus":[69],"limiting":[70],"their":[71],"transferability.":[72],"In":[73,143],"order":[74],"further":[76],"enhance":[77],"transferability":[79,190],"of":[80,129,139,155,164,192],"examples,":[82],"we":[83,167],"propose":[84],"a":[85],"novel":[86],"attack":[88,208],"framework,":[89],"I&CA":[90,110,185],"(Individual":[91],"&":[92],"Common":[93],"feature":[94],"Attack),":[95],"which":[96,159],"simultaneously":[97,168],"considers":[98],"within":[101,117],"each":[102,118],"common":[105,130,165],"cross-modal":[107,133],"interactions.":[108],"Concretely,":[109],"first":[111],"drives":[112],"divergence":[113],"among":[114],"disrupt":[121],"single-modality":[122],"learning,":[123],"then":[125],"suppresses":[126],"expression":[128],"during":[132],"interactions,":[134],"thereby":[135],"undermining":[136],"robustness":[138],"fusion":[141],"mechanism.":[142],"addition,":[144],"prevent":[146],"perturbations":[148],"overfitting":[150],"bias":[154],"modality,":[158],"may":[160],"distort":[161],"representation":[163],"features,":[166],"introduce":[169],"augmentation":[170],"strategies":[171],"both":[173,204],"modalities.":[174],"Across":[175],"various":[176],"experimental":[177],"settings":[178],"widely":[180],"recognized":[181],"benchmarks,":[183],"framework":[186],"achieves":[187],"an":[188],"average":[189],"improvement":[191],"6.15%":[193],"over":[194],"state-of-the-art":[196],"DRA":[197],"method,":[198],"delivering":[199],"significant":[200],"performance":[201],"gains":[202],"cross-model":[205],"cross-task":[207]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-29T00:00:00"}