{"id":"https://openalex.org/W3093455776","doi":"https://doi.org/10.1145/3394171.3414009","title":"Attacking Image Captioning Towards Accuracy-Preserving Target Words Removal","display_name":"Attacking Image Captioning Towards Accuracy-Preserving Target Words Removal","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3093455776","doi":"https://doi.org/10.1145/3394171.3414009","mag":"3093455776"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3414009","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3414009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th 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/A5084510895","display_name":"Jiayi Ji","orcid":"https://orcid.org/0000-0002-9956-6308"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Ji","raw_affiliation_strings":["Xiamen University, Xiamen City, Fujian Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen City, Fujian Province, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059926864","display_name":"Xiaoshuai Sun","orcid":"https://orcid.org/0000-0003-3912-9306"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshuai Sun","raw_affiliation_strings":["Xiamen University, Xiamen City, Fujian Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen City, Fujian Province, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091531008","display_name":"Yiyi Zhou","orcid":"https://orcid.org/0000-0002-5110-4526"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiyi Zhou","raw_affiliation_strings":["Xiamen University, Xiamen City, Fujian Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen City, Fujian Province, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016080094","display_name":"Rongrong Ji","orcid":"https://orcid.org/0000-0001-9163-2932"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Ji","raw_affiliation_strings":["Xiamen University, Xiamen City, Fujian Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen City, Fujian Province, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008400844","display_name":"Fuhai Chen","orcid":"https://orcid.org/0000-0001-5441-5998"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuhai Chen","raw_affiliation_strings":["Xiamen University, Xiamen City, Fujian Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen City, Fujian Province, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039205892","display_name":"Jianzhuang Liu","orcid":"https://orcid.org/0000-0002-7960-9382"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzhuang Liu","raw_affiliation_strings":["Noah's Ark Lab, Huawei Technologies, Beijing City, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Noah's Ark Lab, Huawei Technologies, Beijing City, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111504451","display_name":"Qi Tian","orcid":"https://orcid.org/0000-0002-5165-4325"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Tian","raw_affiliation_strings":["Huawei Cloud BU, Huawei Technologies, Beijing City, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Cloud BU, Huawei Technologies, Beijing City, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"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":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4226","last_page":"4234"},"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":0.9915000200271606,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9858999848365784,"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":0.9864587187767029},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7956883311271667},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6558952331542969},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6015834808349609},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5979520678520203},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5398596525192261},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5350782871246338},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5265277624130249},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49695804715156555},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.384552538394928},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3692764341831207},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36779212951660156},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36443954706192017},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10287874937057495},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07104501128196716}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9864587187767029},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7956883311271667},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6558952331542969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6015834808349609},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5979520678520203},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5398596525192261},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5350782871246338},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5265277624130249},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49695804715156555},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.384552538394928},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3692764341831207},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36779212951660156},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36443954706192017},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10287874937057495},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07104501128196716},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3414009","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3414009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W1673923490","https://openalex.org/W1895577753","https://openalex.org/W1903029394","https://openalex.org/W1905882502","https://openalex.org/W1945616565","https://openalex.org/W2101105183","https://openalex.org/W2102605133","https://openalex.org/W2137226992","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2243397390","https://openalex.org/W2460937040","https://openalex.org/W2528287124","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2755542034","https://openalex.org/W2788277448","https://openalex.org/W2901988662","https://openalex.org/W2954182683","https://openalex.org/W2962861647","https://openalex.org/W2962995403","https://openalex.org/W2963084599","https://openalex.org/W2963857521","https://openalex.org/W2970569830","https://openalex.org/W2982260276","https://openalex.org/W2982553922","https://openalex.org/W2986670728","https://openalex.org/W2988793532","https://openalex.org/W3008585839","https://openalex.org/W3034984754"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W3217195652"],"abstract_inverted_index":{"In":[0],"this":[1,59,89,124],"paper,":[2],"we":[3,25,81,140],"investigate":[4],"the":[5,28,49,53,104,114,149,166],"fragility":[6],"of":[7],"deep":[8],"image":[9,33],"captioning":[10,50,78,130,188],"models":[11],"against":[12],"adversarial":[13,29,43,85,100],"attacks.":[14],"Different":[15],"from":[16,39],"existing":[17],"works":[18],"that":[19,165],"generate":[20],"common":[21],"words":[22,38,178],"and":[23,73,95,133,175,182],"concepts,":[24],"focus":[26],"on":[27,148,185],"attacks":[30,171],"towards":[31],"controllable":[32],"captioning,":[34],"i.e.,":[35,126],"removing":[36,173],"target":[37,105,177],"captions":[40],"by":[41,172],"imposing":[42],"noises":[44],"to":[45,70,102],"images":[46],"while":[47,112,179],"maintaining":[48,180],"accuracy":[51,131],"for":[52,76,88,145],"remaining":[54],"visual":[55],"content.":[56],"We":[57],"name":[58],"new":[60,90,156],"task":[61],"as":[62],"Masked":[63],"Image":[64],"Captioning":[65],"(MIC),":[66],"which":[67,98],"is":[68],"expected":[69],"be":[71],"training":[72,113],"labeling":[74],"free":[75],"end-to-end":[77],"models.":[79],"Meanwhile,":[80],"propose":[82,141],"a":[83,142,155],"novel":[84,119],"learning":[86],"approach":[87,168],"task,":[91],"termed":[92],"Show,":[93],"Mask,":[94],"Tell":[96],"(SMT),":[97],"crafts":[99],"examples":[101],"mask":[103],"concepts":[106],"via":[107],"minimizing":[108],"an":[109],"objective":[110],"loss":[111],"noise":[115,134],"generator.":[116],"Concretely,":[117],"three":[118],"designs":[120],"are":[121],"introduced":[122],"in":[123],"loss,":[125],"word":[127],"removal":[128],"regularization,":[129,132],"filtering":[135],"regularization.":[136],"For":[137],"quantitative":[138],"validation,":[139],"benchmark":[143],"dataset":[144],"MIC":[146],"based":[147],"MS":[150],"COCO":[151],"dataset,":[152],"together":[153],"with":[154],"evaluation":[157],"metric":[158],"called":[159],"Attack":[160],"Quality.":[161],"Experimental":[162],"results":[163],"show":[164],"proposed":[167],"achieves":[169],"successful":[170],"93.8%":[174],"91.9%":[176],"97.3%":[181],"97.4%":[183],"accuracies":[184],"two":[186],"cutting-edge":[187],"models,":[189],"respectively.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}