{"id":"https://openalex.org/W4414360094","doi":"https://doi.org/10.24963/ijcai.2025/127","title":"Poisoning-based Backdoor Attacks for Arbitrary Target Label with Positive Triggers","display_name":"Poisoning-based Backdoor Attacks for Arbitrary Target Label with Positive Triggers","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360094","doi":"https://doi.org/10.24963/ijcai.2025/127"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/127","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5113204636","display_name":"Binxiao Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Binxiao Huang","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072120057","display_name":"Ngai Wong","orcid":"https://orcid.org/0000-0002-3026-0108"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ngai Wong","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1134","last_page":"1142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9315999746322632,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9315999746322632,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/backdoor","display_name":"Backdoor","score":0.9955000281333923},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7124000191688538},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5515000224113464},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.48089998960494995},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4341000020503998},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.391400009393692},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.3815999925136566},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36649999022483826}],"concepts":[{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.9955000281333923},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7287999987602234},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7124000191688538},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5515000224113464},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.48089998960494995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4693000018596649},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4341000020503998},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.4050000011920929},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.350600004196167},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30489999055862427},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2955000102519989},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C95922358","wikidata":"https://www.wikidata.org/wiki/Q5432725","display_name":"False positive rate","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C2780741293","wikidata":"https://www.wikidata.org/wiki/Q4818019","display_name":"Attack patterns","level":3,"score":0.2596000134944916},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/127","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Poisoning-based":[0,102],"backdoor":[1,79,103,205],"attacks":[2,80],"expose":[3],"vulnerabilities":[4],"during":[5],"the":[6,20,47,52,58,62,75,118,122,129,134,145,173,196],"data":[7,35],"preparation":[8],"phase":[9],"of":[10,78,90,125,203],"deep":[11],"neural":[12],"network":[13,59],"(DNN)":[14],"training.":[15],"The":[16],"DNNs":[17],"trained":[18,60,132],"on":[19,33,133],"poisoned":[21,135],"dataset":[22,64],"will":[23],"be":[24],"embedded":[25],"with":[26,105,156],"a":[27,41,66,87,98,157,177,201],"backdoor,":[28],"making":[29],"them":[30,115],"behave":[31],"well":[32],"clean":[34,63],"while":[36],"outputting":[37],"malicious":[38],"predictions":[39],"whenever":[40],"trigger":[42,67,142],"is":[43,131],"applied.":[44],"To":[45],"exploit":[46],"abundant":[48],"information":[49],"contained":[50],"in":[51,121],"input-to-label":[53],"mapping,":[54],"our":[55],"scheme":[56],"utilizes":[57],"from":[61],"as":[65],"generator":[68],"to":[69,113,117,143,152],"produce":[70],"poisons":[71],"that":[72,172],"significantly":[73],"raise":[74],"success":[76,180],"rate":[77,181],"versus":[81],"conventional":[82],"approaches.":[83],"Specifically,":[84],"we":[85,137,169],"introduce":[86],"new":[88],"categorization":[89],"triggers":[91],"inspired":[92],"by":[93],"adversarial":[94],"techniques":[95],"and":[96,100,166,192],"propose":[97],"multi-label":[99],"multi-payload":[101],"attack":[104,175,179,198],"Positive":[106],"Triggers":[107],"(PPT),":[108],"which":[109],"strategically":[110],"manipulates":[111],"inputs":[112],"align":[114],"closer":[116],"target":[119,154],"label":[120,155],"feature":[123],"space":[124],"benign":[126],"classifiers.":[127],"Once":[128],"classifier":[130,147],"dataset,":[136],"can":[138,199],"generate":[139],"an":[140],"input-label-aware":[141],"make":[144],"infected":[146],"predict":[148],"any":[149,153],"given":[150],"input":[151],"high":[158,178],"possibility.":[159],"Through":[160],"extensive":[161],"experiments":[162],"under":[163],"both":[164],"dirty-label":[165],"clean-label":[167],"settings,":[168],"demonstrate":[170],"empirically":[171],"proposed":[174],"achieves":[176],"without":[182],"sacrificing":[183],"accuracy":[184],"across":[185],"various":[186],"datasets,":[187],"including":[188],"SVHN,":[189],"CIFAR10,":[190],"GTSRB,":[191],"Tiny":[193],"ImageNet.":[194],"Additionally,":[195],"PPT":[197],"elude":[200],"variety":[202],"classical":[204],"defenses,":[206],"proving":[207],"its":[208],"effectiveness.":[209]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}