{"id":"https://openalex.org/W4403791752","doi":"https://doi.org/10.1145/3664647.3686835","title":"Sample-agnostic Adversarial Perturbation for Vision-Language Pre-training Models","display_name":"Sample-agnostic Adversarial Perturbation for Vision-Language Pre-training Models","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791752","doi":"https://doi.org/10.1145/3664647.3686835"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3686835","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3686835","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, Northwest Polytechnical University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0009-2017-962X","affiliations":[{"raw_affiliation_string":"School of Electronics and Information, Northwest 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":"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":"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":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9749","last_page":"9758"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9988999962806702,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.996999979019165,"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":0.8968150019645691},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7207568883895874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5227736830711365},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4928441047668457},{"id":"https://openalex.org/keywords/perturbation","display_name":"Perturbation (astronomy)","score":0.4785069525241852},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.44373130798339844},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36358797550201416}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8968150019645691},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7207568883895874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5227736830711365},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4928441047668457},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.4785069525241852},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.44373130798339844},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36358797550201416},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3686835","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3686835","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":0.44999998807907104}],"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/W2007972815","https://openalex.org/W2106277773","https://openalex.org/W2108598243","https://openalex.org/W2187089797","https://openalex.org/W2243397390","https://openalex.org/W2543927648","https://openalex.org/W2558687840","https://openalex.org/W2593390416","https://openalex.org/W2885039223","https://openalex.org/W2897135094","https://openalex.org/W2963047332","https://openalex.org/W2963855547","https://openalex.org/W2997502936","https://openalex.org/W3037773948","https://openalex.org/W3038649929","https://openalex.org/W3090449556","https://openalex.org/W3173220247","https://openalex.org/W3176463841","https://openalex.org/W4283317927","https://openalex.org/W4312310776","https://openalex.org/W4312877428","https://openalex.org/W4313126997","https://openalex.org/W4322576838","https://openalex.org/W4387967929","https://openalex.org/W4387968071","https://openalex.org/W4390889737","https://openalex.org/W4400611426","https://openalex.org/W4400903918","https://openalex.org/W4403791218"],"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":{"Recent":[0],"studies":[1],"on":[2,110],"AI":[3],"security":[4],"have":[5],"highlighted":[6],"the":[7,53,60,69,90,97,104,154,162,172,183],"vulnerability":[8],"of":[9,55,71,93,165,174,185],"Vision-Language":[10],"Pre-training":[11],"(VLP)":[12],"models":[13,198],"to":[14,48,67,78,85,99,132,160],"subtle":[15],"yet":[16],"intentionally":[17],"designed":[18],"perturbations":[19,176],"in":[20,33,113],"images":[21],"and":[22,119,126,137,192,199],"texts.":[23],"Investigating":[24],"multimodal":[25,37,64],"systems'":[26],"robustness":[27],"via":[28],"adversarial":[29,50,178],"attacks":[30,38,102],"is":[31,59,158],"crucial":[32],"this":[34,111],"field.":[35],"Most":[36],"are":[39],"sample-specific,":[40],"generating":[41],"a":[42,72,145,150],"unique":[43],"perturbation":[44,75],"for":[45],"each":[46],"sample":[47,87,124],"construct":[49],"samples.":[51],"To":[52],"best":[54],"our":[56,186],"knowledge,":[57],"it":[58],"first":[61],"work":[62],"through":[63],"decision":[65,91,127,135],"boundaries":[66,92],"explore":[68,83],"creation":[70,173],"universal,":[73],"sample-agnostic":[74],"that":[76],"applies":[77],"any":[79],"image.":[80],"Initially,":[81],"we":[82,116],"strategies":[84],"move":[86],"points":[88,125],"beyond":[89],"linear":[94],"classifiers,":[95],"refining":[96],"algorithm":[98],"ensure":[100],"successful":[101],"under":[103],"top":[105],"k":[106],"accuracy":[107],"metric.":[108],"Based":[109],"foundation,":[112],"visual-language":[114],"tasks,":[115],"treat":[117],"visual":[118],"textual":[120],"modalities":[121],"as":[122],"reciprocal":[123],"hyperplanes,":[128],"guiding":[129],"image":[130],"embeddings":[131],"traverse":[133],"text-constructed":[134],"boundaries,":[136],"vice":[138],"versa.":[139],"This":[140],"iterative":[141],"process":[142],"consistently":[143],"refines":[144],"universal":[146],"perturbation,":[147],"ultimately":[148],"identifying":[149],"singular":[151],"direction":[152],"within":[153],"input":[155],"space":[156],"which":[157],"exploitable":[159],"impair":[161],"retrieval":[163],"performance":[164],"VLP":[166,197],"models.":[167],"The":[168],"proposed":[169],"algorithms":[170],"support":[171],"global":[175],"or":[177],"patches.":[179],"Comprehensive":[180],"experiments":[181],"validate":[182],"effectiveness":[184],"method,":[187],"showcasing":[188],"its":[189],"data,":[190],"task,":[191],"model":[193],"transferability":[194],"across":[195],"various":[196],"datasets.":[200],"Code:":[201],"https://github.com/LibertazZ/MUAP":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}