{"id":"https://openalex.org/W4412082085","doi":"https://doi.org/10.1109/tifs.2025.3586430","title":"Enhancing the Robustness of Vision-Language Foundation Models by Alignment Perturbation","display_name":"Enhancing the Robustness of Vision-Language Foundation Models by Alignment Perturbation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412082085","doi":"https://doi.org/10.1109/tifs.2025.3586430"},"language":"en","primary_location":{"id":"doi:10.1109/tifs.2025.3586430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2025.3586430","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101865604","display_name":"Cong Zhang","orcid":"https://orcid.org/0000-0002-5269-7749"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Zhang","raw_affiliation_strings":["School of Intelligence Science and Technology, University of Science and Technology Beijing, Beijing, China","University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0002-5269-7749","affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669242","display_name":"Shuhui Wang","orcid":"https://orcid.org/0000-0002-5931-0527"},"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhui Wang","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China","Institute of Computing Technology, Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0002-5931-0527","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433314","display_name":"Xiaodan Li","orcid":"https://orcid.org/0000-0002-5025-4805"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodan Li","raw_affiliation_strings":["Alibaba Group, Hangzhou, China","Alibaba Group, China"],"raw_orcid":"https://orcid.org/0000-0002-5025-4805","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101567069","display_name":"Yao Zhu","orcid":"https://orcid.org/0000-0003-0991-1970"},"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":"Yao Zhu","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0991-1970","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047226078","display_name":"Honggang Qi","orcid":"https://orcid.org/0000-0002-7947-1491"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honggang Qi","raw_affiliation_strings":["School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0002-7947-1491","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028597017","display_name":"Qingming Huang","orcid":"https://orcid.org/0000-0001-7542-296X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingming Huang","raw_affiliation_strings":["School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0001-7542-296X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2966,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.88817447,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"20","issue":null,"first_page":"7091","last_page":"7105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9365000128746033,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9365000128746033,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9060999751091003,"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/computer-science","display_name":"Computer science","score":0.7677594423294067},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7422974705696106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45092955231666565},{"id":"https://openalex.org/keywords/perturbation","display_name":"Perturbation (astronomy)","score":0.4126850366592407},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38192105293273926}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7677594423294067},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7422974705696106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45092955231666565},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.4126850366592407},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38192105293273926},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tifs.2025.3586430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2025.3586430","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.44999998807907104,"display_name":"Climate action"}],"awards":[{"id":"https://openalex.org/G1619870141","display_name":null,"funder_award_id":"2023YFC2508704","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4199693610","display_name":null,"funder_award_id":"62236008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5327851226","display_name":null,"funder_award_id":"62022083","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6212863906","display_name":null,"funder_award_id":"U21B2038","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/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":74,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2560730294","https://openalex.org/W2954182683","https://openalex.org/W2963857521","https://openalex.org/W3100355250","https://openalex.org/W4225796928","https://openalex.org/W4226110825","https://openalex.org/W4283317927","https://openalex.org/W4293846201","https://openalex.org/W4312648479","https://openalex.org/W4312933868","https://openalex.org/W4385574156","https://openalex.org/W4385574358","https://openalex.org/W4386071707","https://openalex.org/W4386076140","https://openalex.org/W4390190425","https://openalex.org/W4390871741","https://openalex.org/W4390874189","https://openalex.org/W4393157467","https://openalex.org/W4394586040","https://openalex.org/W4400189006","https://openalex.org/W4400315070","https://openalex.org/W4400579908","https://openalex.org/W4401072559","https://openalex.org/W4401212199","https://openalex.org/W4402671651","https://openalex.org/W4402713133","https://openalex.org/W4402727057","https://openalex.org/W4402753692","https://openalex.org/W4402754146","https://openalex.org/W4402754214","https://openalex.org/W4402774109","https://openalex.org/W4402855384","https://openalex.org/W4403791397","https://openalex.org/W4404534210","https://openalex.org/W6640425456","https://openalex.org/W6758975236","https://openalex.org/W6791353385","https://openalex.org/W6796581206","https://openalex.org/W6798805250","https://openalex.org/W6803316292","https://openalex.org/W6810334672","https://openalex.org/W6811013733","https://openalex.org/W6811340617","https://openalex.org/W6842836685","https://openalex.org/W6846540555","https://openalex.org/W6847311340","https://openalex.org/W6849177959","https://openalex.org/W6849783008","https://openalex.org/W6850389943","https://openalex.org/W6851592950","https://openalex.org/W6851950068","https://openalex.org/W6852447913","https://openalex.org/W6852874933","https://openalex.org/W6853116092","https://openalex.org/W6853255756","https://openalex.org/W6853835462","https://openalex.org/W6854262950","https://openalex.org/W6854441167","https://openalex.org/W6854866820","https://openalex.org/W6855055401","https://openalex.org/W6855350031","https://openalex.org/W6855469472","https://openalex.org/W6856559388","https://openalex.org/W6856669996","https://openalex.org/W6856794988","https://openalex.org/W6857083971","https://openalex.org/W6857305977","https://openalex.org/W6857569170","https://openalex.org/W6858216746","https://openalex.org/W6858268588","https://openalex.org/W6861291810","https://openalex.org/W6861974593","https://openalex.org/W6869127715"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"While":[0],"Vision-Language":[1],"Models":[2],"(VLMs)":[3],"based":[4],"on":[5,17,27,143],"large-scale":[6],"models":[7,175],"have":[8],"shown":[9],"revolutionary":[10],"advancements":[11],"across":[12,171],"various":[13,67,172],"vision-language":[14],"tasks,":[15],"research":[16],"improving":[18],"VLM":[19,29,51,64,75,112,156,194],"robustness":[20,65,157],"remains":[21],"underexplored.":[22],"Existing":[23],"studies":[24],"primarily":[25],"focus":[26],"attacking":[28],"after":[30],"the":[31,85,127,144,160,177,180,191],"pretrained":[32],"visual":[33,117,137],"or":[34,41,118],"textual":[35,95,103,119,139],"encoders,":[36],"typically":[37],"requiring":[38],"obvious":[39],"noise":[40],"long":[42],"inference":[43],"time.":[44],"In":[45],"this":[46],"study,":[47],"we":[48,73,148],"look":[49],"into":[50],"structure":[52],"and":[53,79,83,94,106,138,174,184,199],"highlight":[54],"alignment":[55,86,145,150,163,182,185],"module\u2019s":[56],"role":[57],"as":[58],"a":[59],"protective":[60],"filter":[61],"that":[62],"enhances":[63],"against":[66],"perturbations.":[68,96],"Motivated":[69],"by":[70,158],"these":[71],"insights,":[72],"investigate":[74],"from":[76],"both":[77,136],"user":[78],"model":[80],"developer":[81],"perspectives":[82],"introduce":[84],"perturbation":[87,98,146,183],"strategy,":[88,147],"which":[89,153],"consists":[90],"of":[91,130,162,179,193],"multimodal,":[92],"visual,":[93],"Multimodal":[97],"aims":[99],"to":[100,110,116,123,135],"achieve":[101],"targeted":[102],"output":[104,129],"generation":[105],"is":[107],"further":[108],"utilized":[109],"enhance":[111],"robustness.":[113],"Minimal":[114],"perturbations":[115],"inputs":[120],"can":[121],"lead":[122],"significant":[124],"changes":[125],"in":[126],"overall":[128],"VLMs,":[131],"revealing":[132],"their":[133],"sensitivity":[134],"input":[140],"variations.":[141],"Building":[142],"propose":[149],"robust":[151,186],"training,":[152],"efficiently":[154],"improves":[155],"finetuning":[159],"parameters":[161],"module":[164],"without":[165],"excessive":[166],"resource":[167],"consumption.":[168],"Experiment":[169],"results":[170],"tasks":[173],"demonstrate":[176],"effectiveness":[178],"proposed":[181],"training.":[187],"These":[188],"methods":[189],"deepen":[190],"understanding":[192],"robustness,":[195],"allowing":[196],"for":[197],"secure":[198],"reliable":[200],"deployment":[201],"towards":[202],"diverse":[203],"real-world":[204],"scenarios.":[205],"Codes":[206],"are":[207],"available":[208],"at":[209],"https://github.com/zhangconghhh/RobustVLMs.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}