{"id":"https://openalex.org/W7133952716","doi":"https://doi.org/10.1109/tifs.2026.3671065","title":"Are Large Vision-Language Models Robust to Adversarial Visual Transformations?","display_name":"Are Large Vision-Language Models Robust to Adversarial Visual Transformations?","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7133952716","doi":"https://doi.org/10.1109/tifs.2026.3671065"},"language":null,"primary_location":{"id":"doi:10.1109/tifs.2026.3671065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2026.3671065","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/A5124224535","display_name":"Daizong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daizong Liu","raw_affiliation_strings":["Institute for Math &#x26; AI, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-8179-4508","affiliations":[{"raw_affiliation_string":"Institute for Math &#x26; AI, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128203517","display_name":"Xiaowen Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210157617","display_name":"Huazhong University of Science and Technology Hospital","ror":"https://ror.org/05f9vfg11","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210157617"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowen Cai","raw_affiliation_strings":["Shenzhen Huazhong University of Science and Technology Research Institute, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Huazhong University of Science and Technology Research Institute, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I4210157617","https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128141580","display_name":"Pan Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210157617","display_name":"Huazhong University of Science and Technology Hospital","ror":"https://ror.org/05f9vfg11","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210157617"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan Zhou","raw_affiliation_strings":["Shenzhen Huazhong University of Science and Technology Research Institute, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-8629-4622","affiliations":[{"raw_affiliation_string":"Shenzhen Huazhong University of Science and Technology Research Institute, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I4210157617","https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065871371","display_name":"Xiaoye Qu","orcid":"https://orcid.org/0000-0002-4907-3978"},"institutions":[{"id":"https://openalex.org/I4210157617","display_name":"Huazhong University of Science and Technology Hospital","ror":"https://ror.org/05f9vfg11","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210157617"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoye Qu","raw_affiliation_strings":["Shenzhen Huazhong University of Science and Technology Research Institute, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-4907-3978","affiliations":[{"raw_affiliation_string":"Shenzhen Huazhong University of Science and Technology Research Institute, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I4210157617","https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128179811","display_name":"Lichao Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lichao Sun","raw_affiliation_strings":["Department of Computer Science and Engineering, Lehigh University, Bethlehem, PA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1539-7939","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Lehigh University, Bethlehem, PA, USA","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128172350","display_name":"Wei Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Hu","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9860-0922","affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.2709,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9567273,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"21","issue":null,"first_page":"2564","last_page":"2579"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1907999962568283,"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":0.1907999962568283,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.179299995303154,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11680000275373459,"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":0.7170000076293945},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4221000075340271},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41670000553131104},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.29649999737739563},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2919999957084656},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.2847999930381775},{"id":"https://openalex.org/keywords/algorithm-design","display_name":"Algorithm design","score":0.2759000062942505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7990000247955322},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7170000076293945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5041000247001648},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4221000075340271},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41670000553131104},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3411000072956085},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.2847999930381775},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2599000036716461},{"id":"https://openalex.org/C3020028006","wikidata":"https://www.wikidata.org/wiki/Q9158","display_name":"Electronic mail","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25679999589920044},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tifs.2026.3671065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2026.3671065","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":[],"awards":[{"id":"https://openalex.org/G3118938122","display_name":null,"funder_award_id":"2025ZD0123602","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G6130798805","display_name":null,"funder_award_id":"JCYJ20250604191037048","funder_id":"https://openalex.org/F4320336736","funder_display_name":"Chengdu Science and Technology Program"},{"id":"https://openalex.org/G664739573","display_name":null,"funder_award_id":"62476107","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/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320336736","display_name":"Chengdu Science and Technology Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2302255633","https://openalex.org/W2543927648","https://openalex.org/W2560730294","https://openalex.org/W2765407302","https://openalex.org/W2774644650","https://openalex.org/W2796314858","https://openalex.org/W2949736877","https://openalex.org/W2963857521","https://openalex.org/W2969542116","https://openalex.org/W2970641574","https://openalex.org/W2992308087","https://openalex.org/W3134815184","https://openalex.org/W3202281277","https://openalex.org/W3216468633","https://openalex.org/W4386113300","https://openalex.org/W4389352409","https://openalex.org/W4390190425","https://openalex.org/W4390871946","https://openalex.org/W4393157467","https://openalex.org/W4402288734","https://openalex.org/W4403791703","https://openalex.org/W4405718359","https://openalex.org/W4405786817","https://openalex.org/W4406611059","https://openalex.org/W4406857481","https://openalex.org/W4410852834","https://openalex.org/W4411799673","https://openalex.org/W4412082085","https://openalex.org/W4413000956","https://openalex.org/W4413144966","https://openalex.org/W4413145712","https://openalex.org/W4413147762","https://openalex.org/W4413277723","https://openalex.org/W4414196751","https://openalex.org/W4415797526","https://openalex.org/W4416604145","https://openalex.org/W7133220561"],"related_works":[],"abstract_inverted_index":{"Large":[0],"vision-language":[1],"models":[2],"(LVLMs)":[3],"have":[4,75],"demonstrated":[5],"remarkable":[6],"capabilities":[7],"across":[8],"a":[9],"wide":[10],"range":[11],"of":[12,71,118,143,162,174,206],"multimodal":[13],"understanding":[14],"and":[15,50,73,108,191],"reasoning":[16],"tasks.":[17],"However,":[18],"recent":[19],"research":[20,106],"shows":[21],"that":[22,138,195],"LVLMs":[23,68,207],"are":[24],"susceptible":[25],"to":[26,42,67,98,122,129,155,168,179,208],"adversarial":[27,54,93,120,154,160,209],"examples.":[28],"Existing":[29],"attackers":[30],"either":[31],"optimize":[32],"the":[33,36,44,100,114,140,144,156,171,180,188,203],"perturbations":[34],"on":[35,52],"visual":[37,58,94,123,163,210],"input":[38],"or":[39],"manipulate":[40],"prompts":[41],"fool":[43],"LVLM":[45,101,157],"models,":[46],"requiring":[47],"extensive":[48],"design":[49],"engineering":[51],"these":[53],"manipulations.":[55],"While":[56],"straightforward":[57],"transformation":[59,132],"can":[60,149,198],"boast":[61],"training":[62],"generalization-ability,":[63],"its":[64],"potential":[65,204],"risks":[66],"in":[69],"terms":[70],"safety":[72],"trustworthiness":[74],"been":[76],"largely":[77],"neglected.":[78],"In":[79],"this":[80,105,196],"paper,":[81],"we":[82,112,148],"ask":[83],"an":[84],"intriguing":[85],"question:":[86],"<italic":[87],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[88],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">can":[89],"simple":[90],"yet":[91],"easy-to-implement":[92],"transformations":[95,124,164,178],"be":[96],"utilized":[97],"attack":[99,110,189],"models?</i>":[102],"Motivated":[103],"by":[104,125],"gap":[107],"new":[109],"setting,":[111],"propose":[113],"first":[115],"comprehensive":[116],"assessment":[117],"LVLMs\u2019":[119,127],"robustness":[121],"testing":[126],"resilience":[128],"all":[130,175],"possible":[131],"operations.":[133],"Our":[134],"empirical":[135],"observations":[136],"suggest":[137],"with":[139],"appropriate":[141],"combination":[142],"most":[145],"harmful":[146,177],"transformations,":[147],"build":[150],"transformation-based":[151],"attacks":[152],"more":[153],"models.":[158],"Moreover,":[159],"learning":[161],"is":[165],"further":[166],"introduced":[167],"adaptively":[169],"apply":[170],"malicious":[172],"impacts":[173],"potentially":[176],"raw":[181],"images":[182],"via":[183],"gradient":[184],"approximation":[185],"for":[186],"improving":[187],"effectiveness":[190],"imperceptibility.":[192],"We":[193],"hope":[194],"study":[197],"provide":[199],"deeper":[200],"insights":[201],"into":[202],"vulnerability":[205],"transformations.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-03-06T00:00:00"}