{"id":"https://openalex.org/W2962995403","doi":"https://doi.org/10.18653/v1/p18-1241","title":"Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning","display_name":"Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2962995403","doi":"https://doi.org/10.18653/v1/p18-1241","mag":"2962995403"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-1241","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1241","pdf_url":"https://www.aclweb.org/anthology/P18-1241.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P18-1241.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062177930","display_name":"Hongge Chen","orcid":"https://orcid.org/0000-0002-7519-7341"},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongge Chen","raw_affiliation_strings":["MIT, Cambridge, MA 02139, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I4210110987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100356963","display_name":"Huan Zhang","orcid":"https://orcid.org/0000-0002-5507-4985"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050344371","display_name":"Pin\u2010Yu Chen","orcid":"https://orcid.org/0000-0003-1039-8369"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pin-Yu Chen","raw_affiliation_strings":["IBM Research, NY 10598, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, NY 10598, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030837133","display_name":"Jinfeng Yi","orcid":"https://orcid.org/0000-0003-2149-0670"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinfeng Yi","raw_affiliation_strings":["JD AI Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010841999","display_name":"Cho\u2010Jui Hsieh","orcid":"https://orcid.org/0000-0002-3520-9627"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cho-Jui Hsieh","raw_affiliation_strings":["UC Davis, Davis, CA 95616, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Davis, Davis, CA 95616, USA","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":112,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2587","last_page":"2597"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9904999732971191,"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":0.9864000082015991,"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/closed-captioning","display_name":"Closed captioning","score":0.9772952795028687},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7995277643203735},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7045763731002808},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6218085289001465},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6141282320022583},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5908714532852173},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5273659825325012},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.49267226457595825},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4155840575695038},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3835594654083252},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37611478567123413},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3444744646549225}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9772952795028687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7995277643203735},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7045763731002808},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6218085289001465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6141282320022583},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5908714532852173},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5273659825325012},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.49267226457595825},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4155840575695038},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3835594654083252},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37611478567123413},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3444744646549225},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p18-1241","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1241","pdf_url":"https://www.aclweb.org/anthology/P18-1241.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p18-1241","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1241","pdf_url":"https://www.aclweb.org/anthology/P18-1241.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2962995403.pdf","grobid_xml":"https://content.openalex.org/works/W2962995403.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1673923490","https://openalex.org/W1811254738","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1895989618","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1933349210","https://openalex.org/W1945616565","https://openalex.org/W1947481528","https://openalex.org/W2101105183","https://openalex.org/W2105103432","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2220981600","https://openalex.org/W2302086703","https://openalex.org/W2325920097","https://openalex.org/W2405756170","https://openalex.org/W2408141691","https://openalex.org/W2463565445","https://openalex.org/W2543927648","https://openalex.org/W2549365021","https://openalex.org/W2558809543","https://openalex.org/W2558834163","https://openalex.org/W2570685808","https://openalex.org/W2583186419","https://openalex.org/W2735159761","https://openalex.org/W2746600820","https://openalex.org/W2768661419","https://openalex.org/W2962706528","https://openalex.org/W2963143316","https://openalex.org/W2963207607","https://openalex.org/W2963351776","https://openalex.org/W2963383024","https://openalex.org/W2963389226","https://openalex.org/W2963612069","https://openalex.org/W2963630207","https://openalex.org/W2963857521","https://openalex.org/W2964018924","https://openalex.org/W2964049455","https://openalex.org/W2964065937","https://openalex.org/W2964082701","https://openalex.org/W2964153729","https://openalex.org/W2964241990","https://openalex.org/W3104379732","https://openalex.org/W3106412272"],"related_works":["https://openalex.org/W2982558732","https://openalex.org/W4288087560","https://openalex.org/W2541791370","https://openalex.org/W2035976912","https://openalex.org/W4385415357","https://openalex.org/W3013006014","https://openalex.org/W3094187672","https://openalex.org/W1999222583","https://openalex.org/W2921707373","https://openalex.org/W2602506882"],"abstract_inverted_index":{"Visual":[0],"language":[1,39,47,146],"grounding":[2,48],"is":[3],"widely":[4],"studied":[5],"in":[6,52,67,144],"modern":[7],"neural":[8,25,35,68,81,138],"image":[9,29,69,82,126,139],"captioning":[10,83,127,140],"systems,":[11],"which":[12,78],"typically":[13],"adopts":[14],"an":[15],"encoder-decoder":[16],"framework":[17],"consisting":[18],"of":[19,46,137],"two":[20,75],"principal":[21],"components:":[22],"a":[23,33,60],"convolutional":[24],"network":[26,36],"(CNN)":[27],"for":[28,38,63],"feature":[30],"extraction":[31],"and":[32,55,115,141],"recurrent":[34],"(RNN)":[37],"caption":[40],"generation.":[41],"To":[42],"study":[43],"the":[44,116],"robustness":[45,135],"to":[49,88,124,133],"adversarial":[50,65,107,117],"perturbations":[51],"machine":[53],"vision":[54],"perception,":[56],"we":[57],"propose":[58],"Show-and-Fool,":[59],"novel":[61,142],"algorithm":[62,73,102],"crafting":[64],"examples":[66,108,118],"captioning.":[70],"The":[71],"proposed":[72],"provides":[74],"evaluation":[76],"approaches,":[77],"check":[79],"whether":[80],"systems":[84],"can":[85,103,119],"be":[86,120],"mislead":[87],"output":[89],"some":[90],"randomly":[91,110],"chosen":[92],"captions":[93,112],"or":[94,113],"keywords.":[95],"Our":[96],"extensive":[97],"experiments":[98],"show":[99],"that":[100],"our":[101,130],"successfully":[104],"craft":[105],"visually-similar":[106],"with":[109],"targeted":[111],"keywords,":[114],"made":[121],"highly":[122],"transferable":[123],"other":[125],"systems.":[128],"Consequently,":[129],"approach":[131],"leads":[132],"new":[134],"implications":[136],"insights":[143],"visual":[145],"grounding.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":32},{"year":2018,"cited_by_count":7}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}