{"id":"https://openalex.org/W4392017259","doi":"https://doi.org/10.1007/s11633-024-1535-z","title":"AICAttack: Adversarial Image Captioning Attack with Attention-based Optimization","display_name":"AICAttack: Adversarial Image Captioning Attack with Attention-based Optimization","publication_year":2025,"publication_date":"2025-07-07","ids":{"openalex":"https://openalex.org/W4392017259","doi":"https://doi.org/10.1007/s11633-024-1535-z"},"language":"en","primary_location":{"id":"doi:10.1007/s11633-024-1535-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-024-1535-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-024-1535-z.pdf","source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11633-024-1535-z.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiyao Li","orcid":"https://orcid.org/0009-0003-8595-0944"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Jiyao Li","raw_affiliation_strings":["School of Computer Science, University of Technology Sydney, Sydney, 2007, Australia"],"raw_orcid":"https://orcid.org/0009-0003-8595-0944","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Technology Sydney, Sydney, 2007, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067440327","display_name":"Mingze Ni","orcid":"https://orcid.org/0000-0003-1220-365X"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mingze Ni","raw_affiliation_strings":["School of Computer Science, University of Technology Sydney, Sydney, 2007, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Technology Sydney, Sydney, 2007, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090991667","display_name":"Yifei Dong","orcid":"https://orcid.org/0000-0002-7995-9657"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yifei Dong","raw_affiliation_strings":["School of Computer Science, University of Technology Sydney, Sydney, 2007, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Technology Sydney, Sydney, 2007, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036801346","display_name":"Tianqing Zhu","orcid":"https://orcid.org/0000-0003-3411-7947"},"institutions":[{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Tianqing Zhu","raw_affiliation_strings":["Faculty of Data Science, City University of Macau, Macau, 999078, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Data Science, City University of Macau, Macau, 999078, China","institution_ids":["https://openalex.org/I6469544"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yongshun Gong","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongshun Gong","raw_affiliation_strings":["School of Software, Shandong University, Jinan, 250100, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, 250100, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-3003-1313"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["School of Computer Science, University of Technology Sydney, Sydney, 2007, Australia"],"raw_orcid":"https://orcid.org/0000-0002-3003-1313","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Technology Sydney, Sydney, 2007, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114017466"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00039936,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"4","first_page":"769","last_page":"782"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.989300012588501,"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":0.989300012588501,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9825000166893005,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9745000004768372,"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/closed-captioning","display_name":"Closed captioning","score":0.9667502045631409},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.870238184928894},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6341765522956848},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6144823431968689},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4221893846988678},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.4055968225002289},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3462636470794678}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9667502045631409},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.870238184928894},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6341765522956848},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6144823431968689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4221893846988678},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.4055968225002289},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3462636470794678}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s11633-024-1535-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-024-1535-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-024-1535-z.pdf","source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2402.11940","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.11940","pdf_url":"https://arxiv.org/pdf/2402.11940","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.2402.11940","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2402.11940","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-journal"}],"best_oa_location":{"id":"doi:10.1007/s11633-024-1535-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-024-1535-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-024-1535-z.pdf","source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392017259.pdf","grobid_xml":"https://content.openalex.org/works/W4392017259.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W3217353253","https://openalex.org/W2194775991","https://openalex.org/W2163605009","https://openalex.org/W1686810756","https://openalex.org/W1945616565","https://openalex.org/W4226182655","https://openalex.org/W2575842049","https://openalex.org/W2963758027","https://openalex.org/W2963096510","https://openalex.org/W2954182683","https://openalex.org/W3216130706","https://openalex.org/W4312820932","https://openalex.org/W3136792391","https://openalex.org/W4292615965","https://openalex.org/W2805933625","https://openalex.org/W4206675125","https://openalex.org/W3209355071","https://openalex.org/W3192652975","https://openalex.org/W6729756640","https://openalex.org/W2640329709","https://openalex.org/W4366993199","https://openalex.org/W2963448658","https://openalex.org/W2604505099","https://openalex.org/W2243397390","https://openalex.org/W2543927648","https://openalex.org/W2765424254","https://openalex.org/W3097206420","https://openalex.org/W2783155279","https://openalex.org/W2734423986","https://openalex.org/W6640963894","https://openalex.org/W2962995403","https://openalex.org/W2574790321","https://openalex.org/W2803525166","https://openalex.org/W2799244840","https://openalex.org/W2133564696","https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W68733909","https://openalex.org/W2101105183","https://openalex.org/W6682631176","https://openalex.org/W2949128310","https://openalex.org/W4385574358","https://openalex.org/W4318718936","https://openalex.org/W4391092966"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W4298897568","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Abstract":[0],"Recent":[1],"advances":[2],"in":[3,14],"deep":[4],"learning":[5],"research":[6],"have":[7],"shown":[8],"remarkable":[9],"achievements":[10],"across":[11],"many":[12],"tasks":[13],"computer":[15],"vision":[16],"(CV)":[17],"and":[18,28],"natural":[19],"language":[20],"processing":[21],"(NLP).":[22],"At":[23],"the":[24,31,37,85,102,116,119],"intersection":[25],"of":[26,33,118],"CV":[27],"NLP":[29],"is":[30],"problem":[32],"image":[34,58,65],"captioning,":[35],"where":[36],"related":[38],"models\u2019":[39],"robustness":[40],"against":[41,133],"adversarial":[42,54],"attacks":[43],"has":[44],"not":[45],"been":[46],"well":[47],"studied.":[48],"This":[49],"paper":[50],"presents":[51],"a":[52,75,109],"novel":[53],"attack":[55,60,64,77,152],"strategy,":[56],"attention-based":[57,96],"captioning":[59,66],"(AICAttack),":[61],"designed":[62],"to":[63,71,84,114],"models":[67],"through":[68,127],"subtle":[69],"perturbations":[70,117],"images.":[72],"Operating":[73],"within":[74],"black-box":[76],"scenario,":[78],"our":[79,142],"algorithm":[80],"requires":[81],"no":[82],"access":[83],"target":[86],"model\u2019s":[87],"architecture,":[88],"parameters,":[89],"or":[90],"gradient":[91],"information.":[92],"We":[93,123],"introduce":[94],"an":[95],"candidate":[97],"selection":[98],"mechanism":[99],"that":[100,141],"identifies":[101],"optimal":[103],"pixels":[104],"for":[105],"attack,":[106],"followed":[107],"by":[108,148],"customized":[110],"differential":[111],"evolution":[112],"method":[113,143],"optimize":[115],"pixels\u2019":[120],"RGB":[121],"values.":[122],"demonstrate":[124,140],"AICAttack\u2019s":[125],"effectiveness":[126],"extensive":[128],"experiments":[129],"on":[130],"benchmark":[131],"datasets":[132],"multiple":[134],"victim":[135],"models.":[136],"The":[137],"experimental":[138],"results":[139],"outperforms":[144],"current":[145],"leading-edge":[146],"techniques":[147],"achieving":[149],"consistently":[150],"higher":[151],"success":[153],"rates.":[154]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2024-02-22T00:00:00"}