{"id":"https://openalex.org/W4403780628","doi":"https://doi.org/10.1145/3664647.3681524","title":"Poisoning for Debiasing: Fair Recognition via Eliminating Bias Uncovered in Data Poisoning","display_name":"Poisoning for Debiasing: Fair Recognition via Eliminating Bias Uncovered in Data Poisoning","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780628","doi":"https://doi.org/10.1145/3664647.3681524"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681524","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681524","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":"article","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/A5100388041","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0001-6586-1037"},"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":true,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["Huawei Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065838678","display_name":"Zhefeng Wang","orcid":"https://orcid.org/0000-0001-6703-2064"},"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":"Zhefeng Wang","raw_affiliation_strings":["Huawei Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101675124","display_name":"Rui Hu","orcid":"https://orcid.org/0009-0001-7891-1950"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Hu","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047258925","display_name":"Xinyu Duan","orcid":"https://orcid.org/0000-0002-6803-7964"},"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":"Xinyu Duan","raw_affiliation_strings":["Huawei Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101922350","display_name":"Yi Zheng","orcid":"https://orcid.org/0000-0003-3890-7575"},"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":"Yi Zheng","raw_affiliation_strings":["Huawei Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020858666","display_name":"Baoxing Huai","orcid":"https://orcid.org/0000-0001-9625-2314"},"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":"Baoxing Huai","raw_affiliation_strings":["Huawei Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064073457","display_name":"Jiarun Han","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiarun Han","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023834030","display_name":"Jitao Sang","orcid":"https://orcid.org/0000-0002-0699-3205"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jitao Sang","raw_affiliation_strings":["Beijing Jiaotong University & Peng Cheng Lab, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University & Peng Cheng Lab, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100388041"],"corresponding_institution_ids":["https://openalex.org/I2250955327"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6818659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1866","last_page":"1874"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9990000128746033,"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":0.9990000128746033,"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/debiasing","display_name":"Debiasing","score":0.9843469858169556},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5960203409194946},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.46118173003196716},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23065534234046936},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09672194719314575}],"concepts":[{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.9843469858169556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5960203409194946},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.46118173003196716},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23065534234046936},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09672194719314575}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681524","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681524","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1834627138","https://openalex.org/W2103154003","https://openalex.org/W2194775991","https://openalex.org/W2963116854","https://openalex.org/W2963350032","https://openalex.org/W2963351448","https://openalex.org/W2990270730","https://openalex.org/W2990751682","https://openalex.org/W3098528040","https://openalex.org/W3175547470","https://openalex.org/W3179023856","https://openalex.org/W3187487833","https://openalex.org/W3212259172","https://openalex.org/W3214395392","https://openalex.org/W4212774754","https://openalex.org/W4226316290","https://openalex.org/W4312319992","https://openalex.org/W4312678124","https://openalex.org/W4312901583","https://openalex.org/W4322736917","https://openalex.org/W4382317875","https://openalex.org/W4385965287","https://openalex.org/W4385966003"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4362554880","https://openalex.org/W4281684980","https://openalex.org/W4386875279","https://openalex.org/W2171721708","https://openalex.org/W4390963114","https://openalex.org/W4287887864","https://openalex.org/W3214527415"],"abstract_inverted_index":{"Neural":[0],"networks":[1],"often":[2],"tend":[3],"to":[4,22,31,66,79,104,119,136,148,154,190],"rely":[5],"on":[6,25,44],"bias":[7,48,54,69,81,85],"features":[8,70],"that":[9,27,53,93,170],"have":[10],"strong":[11],"but":[12],"spurious":[13],"correlations":[14],"with":[15],"the":[16,45,84,121,128,134,151,160,168,178,184,187,192,201],"target":[17,77,98,188],"labels":[18,46],"for":[19,71],"decision-making,":[20],"leading":[21],"poor":[23],"performance":[24,204],"data":[26,73,106,117,143,169],"does":[28],"not":[29],"adhere":[30],"these":[32,172,181],"correlations.":[33,174,198],"Early":[34],"debiasing":[35,203],"methods":[36],"typically":[37],"construct":[38],"an":[39],"unbiased":[40],"optimization":[41],"objective":[42],"based":[43],"of":[47,180,186,205],"features.":[49],"Recent":[50],"work":[51],"assumes":[52],"label":[55],"is":[56],"unavailable":[57],"and":[58,75,145],"usually":[59],"trains":[60],"two":[61],"models:":[62],"a":[63,76],"biased":[64,95,125,152,161,173,197],"model":[65,78,146,153,189,193],"deliberately":[67],"learn":[68,137,155],"exposing":[72],"bias,":[74],"eliminate":[80],"captured":[82],"by":[83,124],"model.":[86],"In":[87],"this":[88,110],"paper,":[89],"we":[90,112,141,163,176],"first":[91],"reveal":[92],"previous":[94],"models":[96,126,135],"fit":[97],"labels,":[99],"which":[100,115],"resulted":[101],"in":[102,167,183],"failing":[103],"expose":[105],"bias.":[107,157],"To":[108],"tackle":[109],"issue,":[111],"propose":[113],"poisoner,":[114],"utilizes":[116],"poisoning":[118,144],"embed":[120],"biases":[122],"learned":[123],"into":[127],"poisoned":[129],"training":[130,147,185],"data,":[131],"thereby":[132],"encouraging":[133],"more":[138,156],"biases.":[139],"Specifically,":[140],"couple":[142],"continuously":[149],"prompt":[150],"By":[158],"utilizing":[159],"model,":[162],"can":[164],"identify":[165],"samples":[166,182],"contradict":[171],"Subsequently,":[175],"amplify":[177],"influence":[179],"prevent":[191],"from":[194],"learning":[195],"such":[196],"Experiments":[199],"show":[200],"superior":[202],"our":[206],"method.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}