{"id":"https://openalex.org/W4403791218","doi":"https://doi.org/10.1145/3664647.3681184","title":"A Unified Understanding of Adversarial Vulnerability Regarding Unimodal Models and Vision-Language Pre-training Models","display_name":"A Unified Understanding of Adversarial Vulnerability Regarding Unimodal Models and Vision-Language Pre-training Models","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791218","doi":"https://doi.org/10.1145/3664647.3681184"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681184","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102532202","display_name":"Haonan Zheng","orcid":"https://orcid.org/0009-0009-2017-962X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haonan Zheng","raw_affiliation_strings":["School of Electronics and Information, Northwestern Polytechnical University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0009-2017-962X","affiliations":[{"raw_affiliation_string":"School of Electronics and Information, Northwestern Polytechnical University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100609329","display_name":"Xinyang Deng","orcid":"https://orcid.org/0000-0001-8181-7001"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyang Deng","raw_affiliation_strings":["School of Electronics and Information, Northwestern Polytechnical University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0001-8181-7001","affiliations":[{"raw_affiliation_string":"School of Electronics and Information, Northwestern Polytechnical University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041289658","display_name":"Wen Jiang","orcid":"https://orcid.org/0000-0001-5429-2748"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Jiang","raw_affiliation_strings":["School of Electronics and Information, Northwestern Polytechnical University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0001-5429-2748","affiliations":[{"raw_affiliation_string":"School of Electronics and Information, Northwestern Polytechnical University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046442204","display_name":"Wenrui Li","orcid":"https://orcid.org/0000-0002-2393-9016"},"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":"Wenrui Li","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-2393-9016","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"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":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9972000122070312,"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":0.9972000122070312,"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":0.9786999821662903,"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/T10028","display_name":"Topic Modeling","score":0.9754999876022339,"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/adversarial-system","display_name":"Adversarial system","score":0.8511011004447937},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6673450469970703},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.581575334072113},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.5647293925285339},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5554015636444092},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5449210405349731},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38611674308776855},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37003064155578613},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.14857688546180725},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07597276568412781}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8511011004447937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6673450469970703},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.581575334072113},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.5647293925285339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5554015636444092},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5449210405349731},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38611674308776855},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37003064155578613},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.14857688546180725},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07597276568412781},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681184","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1773149199","https://openalex.org/W2108598243","https://openalex.org/W2243397390","https://openalex.org/W2489487449","https://openalex.org/W2558687840","https://openalex.org/W2560730294","https://openalex.org/W2593390416","https://openalex.org/W2774644650","https://openalex.org/W2897135094","https://openalex.org/W2962858109","https://openalex.org/W2963530300","https://openalex.org/W2963857521","https://openalex.org/W2969542116","https://openalex.org/W3035524453","https://openalex.org/W3035569111","https://openalex.org/W3037773948","https://openalex.org/W3038649929","https://openalex.org/W3101449015","https://openalex.org/W3171288285","https://openalex.org/W4206070857","https://openalex.org/W4283317927","https://openalex.org/W4300072878","https://openalex.org/W4304091674","https://openalex.org/W4312610155","https://openalex.org/W4312877428","https://openalex.org/W4322576838","https://openalex.org/W4387967929","https://openalex.org/W4387968071","https://openalex.org/W4387969040","https://openalex.org/W4390889737"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279","https://openalex.org/W4288019534"],"abstract_inverted_index":{"With":[0],"Vision-Language":[1],"Pre-training":[2],"(VLP)":[3],"models":[4,38,47,66],"demonstrating":[5],"powerful":[6],"multimodal":[7,29,134],"interaction":[8,153],"capabilities,":[9],"the":[10,56,83,97,104,118,122,130,133,152,175,205],"application":[11,124],"scenarios":[12],"of":[13,36,45,58,99,106,125,154,178,207],"neural":[14],"networks":[15],"are":[16,67],"no":[17],"longer":[18],"confined":[19],"to":[20,26,69,95,112,132],"unimodal":[21,37,119,131],"domains":[22],"but":[23],"have":[24,39],"expanded":[25],"more":[27],"complex":[28],"V+L":[30],"downstream":[31,191],"tasks.":[32],"The":[33],"security":[34],"vulnerabilities":[35],"been":[40],"extensively":[41],"examined,":[42],"whereas":[43],"those":[44],"VLP":[46,65,164,208],"remain":[48],"challenging.":[49],"We":[50],"note":[51],"that":[52,91],"in":[53,103,117],"CV":[54],"models,":[55],"understanding":[57],"images":[59],"comes":[60],"from":[61,74,129],"annotated":[62],"information,":[63],"while":[64],"designed":[68],"learn":[70],"image":[71],"representations":[72,94],"directly":[73],"raw":[75],"text.":[76],"Motivated":[77],"by":[78],"this":[79],"discrepancy,":[80],"we":[81,143],"developed":[82],"Feature":[84,145],"Guidance":[85,146],"Attack":[86,149],"(FGA),":[87],"a":[88,200],"novel":[89],"method":[90,181],"uses":[92],"text":[93,139],"direct":[96,123],"perturbation":[98],"clean":[100],"images,":[101],"resulting":[102],"generation":[105],"adversarial":[107],"images.":[108],"FGA":[109],"is":[110],"orthogonal":[111],"many":[113],"advanced":[114],"attack":[115,140,161,186],"strategies":[116],"domain,":[120],"facilitating":[121],"rich":[126],"research":[127],"findings":[128],"scenario.":[135],"By":[136],"appropriately":[137],"introducing":[138],"into":[141],"FGA,":[142],"construct":[144],"with":[147],"Text":[148],"(FGA-T).":[150],"Through":[151],"attacking":[155],"two":[156],"modalities,":[157],"FGA-T":[158],"achieves":[159],"superior":[160],"effects":[162],"against":[163],"models.":[165,209],"Moreover,":[166],"incorporating":[167],"data":[168],"augmentation":[169],"and":[170,184,193,196],"momentum":[171],"mechanisms":[172],"significantly":[173],"improves":[174],"black-box":[176,195],"transferability":[177],"FGA-T.":[179],"Our":[180],"demonstrates":[182],"stable":[183],"effective":[185],"capabilities":[187],"across":[188],"various":[189],"datasets,":[190],"tasks,":[192],"both":[194],"white-box":[197],"settings,":[198],"offering":[199],"unified":[201],"baseline":[202],"for":[203],"exploring":[204],"robustness":[206]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}