{"id":"https://openalex.org/W4405032462","doi":"https://doi.org/10.48550/arxiv.2412.00114","title":"SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments","display_name":"SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments","publication_year":2024,"publication_date":"2024-11-28","ids":{"openalex":"https://openalex.org/W4405032462","doi":"https://doi.org/10.48550/arxiv.2412.00114"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2412.00114","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.00114","pdf_url":"https://arxiv.org/pdf/2412.00114","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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.00114","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088296236","display_name":"Yue Cao","orcid":"https://orcid.org/0000-0002-5433-284X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Cao, Yue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109761751","display_name":"Yun Xing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xing, Yun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115590908","display_name":"Jie Zhang","orcid":"https://orcid.org/0009-0004-7346-8541"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039060932","display_name":"Di Lin","orcid":"https://orcid.org/0000-0002-6904-3370"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Di","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028270700","display_name":"Tianwei Zhang","orcid":"https://orcid.org/0000-0001-6777-1668"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Tianwei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021751767","display_name":"Ivor W. Tsang","orcid":"https://orcid.org/0000-0001-8095-4637"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsang, Ivor","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115602248","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0002-7240-1546"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102442533","display_name":"Qing Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Qing","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5088296236"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9480999708175659,"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":0.9480999708175659,"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":0.9441999793052673,"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/planner","display_name":"Planner","score":0.8086168766021729},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7917089462280273},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6017811894416809},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5241463780403137},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.481764554977417}],"concepts":[{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.8086168766021729},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7917089462280273},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6017811894416809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5241463780403137},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.481764554977417}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2412.00114","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.00114","pdf_url":"https://arxiv.org/pdf/2412.00114","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.2412.00114","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.00114","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.00114","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.00114","pdf_url":"https://arxiv.org/pdf/2412.00114","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":["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":{"Large":[0],"vision-language":[1,216],"models":[2,217],"(LVLMs)":[3],"have":[4],"shown":[5],"remarkable":[6],"capabilities":[7],"in":[8,164,199,214],"interpreting":[9],"visual":[10,52,205],"content.":[11],"While":[12],"existing":[13],"works":[14],"demonstrate":[15,195],"these":[16],"models'":[17],"vulnerability":[18],"to":[19,40,70,73,81,113,155,218],"deliberately":[20],"placed":[21],"adversarial":[22,44,68,93,103,119,177,221],"texts,":[23],"such":[24],"texts":[25],"are":[26],"often":[27],"easily":[28],"identifiable":[29],"as":[30],"anomalous.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35],"present":[36],"the":[37,55,58,77,115,133,144],"first":[38],"approach":[39,62],"generate":[41],"scene-coherent":[42,91,140,176,220],"typographic":[43,92],"attacks":[45,222],"that":[46,96,142,174],"mislead":[47],"advanced":[48],"LVLMs":[49],"while":[50,203],"maintaining":[51,204],"naturalness":[53,206],"through":[54],"capability":[56],"of":[57,190],"LLM-based":[59],"agent.":[60],"Our":[61,193],"addresses":[63],"three":[64],"critical":[65],"questions:":[66],"what":[67],"text":[69,178],"generate,":[71],"where":[72],"place":[74],"it":[75,83],"within":[76,132],"scene,":[78,116],"and":[79,105,125,160,207,223],"how":[80],"integrate":[82],"seamlessly.":[84],"We":[85,151],"propose":[86],"a":[87,98,139,147,196],"training-free,":[88],"multi-modal":[89],"LLM-driven":[90],"planning":[94],"(SceneTAP)":[95],"employs":[97],"three-stage":[99],"process:":[100],"scene":[101],"understanding,":[102],"planning,":[104],"seamless":[106],"integration.":[107],"The":[108],"SceneTAP":[109],"utilizes":[110],"chain-of-thought":[111],"reasoning":[112],"comprehend":[114],"formulate":[117],"effective":[118],"text,":[120],"strategically":[121],"plan":[122],"its":[123,168],"placement,":[124],"provide":[126],"detailed":[127],"instructions":[128],"for":[129],"natural":[130],"integration":[131],"image.":[134],"This":[135,210],"is":[136],"followed":[137],"by":[138,158],"TextDiffuser":[141],"executes":[143],"attack":[145,200],"using":[146],"local":[148],"diffusion":[149],"mechanism.":[150],"extend":[152],"our":[153,175],"method":[154],"real-world":[156],"scenarios":[157],"printing":[159],"placing":[161],"generated":[162],"patches":[163],"physical":[165,191],"environments,":[166],"demonstrating":[167],"practical":[169],"implications.":[170],"Extensive":[171],"experiments":[172],"show":[173],"successfully":[179],"misleads":[180],"state-of-the-art":[181],"LVLMs,":[182],"including":[183],"ChatGPT-4o,":[184],"even":[185],"after":[186],"capturing":[187],"new":[188],"images":[189],"setups.":[192],"evaluations":[194],"significant":[197],"increase":[198],"success":[201],"rates":[202],"contextual":[208],"appropriateness.":[209],"work":[211],"highlights":[212],"vulnerabilities":[213],"current":[215],"sophisticated,":[219],"provides":[224],"insights":[225],"into":[226],"potential":[227],"defense":[228],"mechanisms.":[229]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}