{"id":"https://openalex.org/W4416290867","doi":"https://doi.org/10.1109/iccv51701.2025.00025","title":"One Object, Multiple Lies: A Benchmark for Cross-Task Adversarial Attack on Unified Vision-Language Models","display_name":"One Object, Multiple Lies: A Benchmark for Cross-Task Adversarial Attack on Unified Vision-Language Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416290867","doi":"https://doi.org/10.1109/iccv51701.2025.00025"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.07709","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083804579","display_name":"Jiale Zhao","orcid":"https://orcid.org/0000-0003-0209-8462"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiale Zhao","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011424573","display_name":"Xinyang Jiang","orcid":"https://orcid.org/0000-0002-4991-0596"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyang Jiang","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029286892","display_name":"Junyao Gao","orcid":"https://orcid.org/0009-0007-2270-6820"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyao Gao","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuhao Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Xue","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064237960","display_name":"Cairong Zhao","orcid":"https://orcid.org/0000-0001-6745-9674"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cairong Zhao","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"187","last_page":"196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9465000033378601,"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":0.9465000033378601,"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":0.014399999752640724,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.008100000210106373,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.8689000010490417},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7626000046730042},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6671000123023987},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6301000118255615},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5738000273704529},{"id":"https://openalex.org/keywords/attack-model","display_name":"Attack model","score":0.4327999949455261},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.40459999442100525},{"id":"https://openalex.org/keywords/threat-model","display_name":"Threat model","score":0.38830000162124634}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8689000010490417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.84170001745224},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7626000046730042},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6671000123023987},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6301000118255615},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5738000273704529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.477400004863739},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4659999907016754},{"id":"https://openalex.org/C65856478","wikidata":"https://www.wikidata.org/wiki/Q3991682","display_name":"Attack model","level":2,"score":0.4327999949455261},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C140547941","wikidata":"https://www.wikidata.org/wiki/Q7797194","display_name":"Threat model","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30550000071525574},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2808000147342682},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2736999988555908},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C2778403875","wikidata":"https://www.wikidata.org/wiki/Q20312394","display_name":"Adversarial machine learning","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2581999897956848}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.07709","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.07709","pdf_url":"https://arxiv.org/pdf/2507.07709","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.07709","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.07709","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.07709","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.07709","pdf_url":"https://arxiv.org/pdf/2507.07709","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Unified":[0],"vision-language":[1],"models(VLMs)":[2],"have":[3],"recently":[4],"shown":[5],"remarkable":[6],"progress,":[7],"enabling":[8],"a":[9,21,60,87,96,109],"single":[10],"model":[11],"to":[12,48],"flexibly":[13],"address":[14],"diverse":[15,169],"tasks":[16],"through":[17],"different":[18],"instructions":[19,42],"within":[20],"shared":[22],"computational":[23],"architecture.":[24],"This":[25],"instruction-based":[26],"control":[27],"mechanism":[28],"creates":[29],"unique":[30],"security":[31],"challenges,":[32],"as":[33],"adversarial":[34,75,113],"inputs":[35],"must":[36],"remain":[37],"effective":[38],"across":[39,91,105,168],"multiple":[40],"task":[41],"that":[43,101,143],"may":[44],"be":[45],"unpredictably":[46],"applied":[47],"process":[49],"the":[50,83],"same":[51],"malicious":[52],"content.":[53],"In":[54],"this":[55,117],"paper,":[56],"we":[57,119],"introduce":[58],"CrossVLAD,":[59],"new":[61],"benchmark":[62],"dataset":[63],"carefully":[64],"curated":[65],"from":[66],"MSCOCO":[67],"with":[68,126],"GPT-4-assisted":[69],"annotations":[70],"for":[71],"systematically":[72],"evaluating":[73],"cross-task":[74,152],"attacks":[76],"on":[77,82,135],"unified":[78,140,166],"VLMs.":[79],"CrossVLAD":[80],"centers":[81],"object-change":[84,157],"objective-consistently":[85],"manipulating":[86],"target":[88],"object's":[89],"classification":[90],"four":[92],"downstream":[93],"tasks-and":[94],"proposes":[95],"novel":[97],"success":[98,158],"rate":[99],"metric":[100],"measures":[102],"simultaneous":[103],"misclassification":[104],"all":[106],"tasks,":[107],"providing":[108],"rigorous":[110],"evaluation":[111],"of":[112],"transferability.":[114],"To":[115],"tackle":[116],"challenge,":[118],"present":[120],"CRAFT":[121],"(Cross-task":[122],"Region-based":[123],"Attack":[124],"Framework":[125],"Token-alignment),":[127],"an":[128],"efficient":[129],"region-centric":[130],"attack":[131,153],"method.":[132],"Extensive":[133],"experiments":[134],"Florence-2":[136],"and":[137,155],"other":[138],"popular":[139],"VLMs":[141,167],"demonstrate":[142],"our":[144],"method":[145],"outperforms":[146],"existing":[147],"approaches":[148],"in":[149,163],"both":[150],"overall":[151],"performance":[154],"targeted":[156],"rates,":[159],"highlighting":[160],"its":[161],"effectiveness":[162],"adversarially":[164],"influencing":[165],"tasks.":[170]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}