{"id":"https://openalex.org/W7141187916","doi":"https://doi.org/10.1109/tifs.2026.3678359","title":"One Trigger, Multiple Victims: Clean-Label Neighborhood Backdoor Attacks on Graph Neural Networks","display_name":"One Trigger, Multiple Victims: Clean-Label Neighborhood Backdoor Attacks on Graph Neural Networks","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7141187916","doi":"https://doi.org/10.1109/tifs.2026.3678359"},"language":null,"primary_location":{"id":"doi:10.1109/tifs.2026.3678359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2026.3678359","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Forensics and Security","raw_type":"journal-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":null,"display_name":"Huaxin Deng","orcid":"https://orcid.org/0009-0005-9643-7542"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaxin Deng","raw_affiliation_strings":["School of Cyber Science and Engineering, Sichuan University, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0009-0005-9643-7542","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Sichuan University, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130817103","display_name":"Yong Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Fang","raw_affiliation_strings":["School of Cyber Science and Engineering, Sichuan University, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0003-0708-1686","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Sichuan University, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130759921","display_name":"Qiang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Zhang","raw_affiliation_strings":["School of Cyber Science and Engineering, Sichuan University, Chengdu, Sichuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Sichuan University, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100319564","display_name":"Chengwei Liu","orcid":"https://orcid.org/0000-0003-1175-2753"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengwei Liu","raw_affiliation_strings":["College of Cryptology and Cyber Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-1175-2753","affiliations":[{"raw_affiliation_string":"College of Cryptology and Cyber Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130770759","display_name":"Yang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7300-9215","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024278894","display_name":"Yijia Xu","orcid":"https://orcid.org/0000-0003-2843-4225"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijia Xu","raw_affiliation_strings":["School of Cyber Science and Engineering, Sichuan University, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0003-2843-4225","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Sichuan University, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I24185976"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32586333,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":null,"first_page":"3339","last_page":"3352"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9014999866485596,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9014999866485596,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.06549999862909317,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.004600000102072954,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5134999752044678},{"id":"https://openalex.org/keywords/backdoor","display_name":"Backdoor","score":0.48840001225471497},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.41749998927116394},{"id":"https://openalex.org/keywords/graph-theory","display_name":"Graph theory","score":0.3407000005245209},{"id":"https://openalex.org/keywords/electronic-mail","display_name":"Electronic mail","score":0.3089999854564667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8274000287055969},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5134999752044678},{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.48840001225471497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4343999922275543},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.41749998927116394},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32339999079704285},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3221000134944916},{"id":"https://openalex.org/C3020028006","wikidata":"https://www.wikidata.org/wiki/Q9158","display_name":"Electronic mail","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C178489894","wikidata":"https://www.wikidata.org/wiki/Q8789","display_name":"Cryptography","level":2,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tifs.2026.3678359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2026.3678359","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Forensics and Security","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.42226675152778625,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[{"id":"https://openalex.org/G263632530","display_name":null,"funder_award_id":"U24B20147","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Graph":[0],"Neural":[1],"Networks":[2],"(GNNs)":[3],"have":[4],"achieved":[5],"remarkable":[6],"success":[7,178],"in":[8,72,187,211],"modeling":[9],"structured":[10],"data.":[11],"Recent":[12],"studies,":[13],"however,":[14],"reveal":[15,207],"that":[16,86,171],"they":[17],"are":[18],"highly":[19],"vulnerable":[20],"to":[21,31,111],"backdoor":[22,50,84],"attacks,":[23],"which":[24,68],"can":[25],"implant":[26],"triggers":[27,38],"into":[28],"training":[29,56],"data":[30],"mislead":[32],"predictions":[33],"on":[34,42,54,65,162,180],"nodes":[35,183],"injected":[36],"with":[37,156],"while":[39,62,131],"maintaining":[40],"accuracy":[41],"clean":[43],"inputs.":[44],"Despite":[45],"recent":[46],"advances,":[47],"existing":[48],"graph":[49,83,203,212],"attacks":[51],"often":[52],"rely":[53],"explicit":[55],"interventions":[57],"and":[58,120,145,148,166,184,206],"substantial":[59],"trigger":[60,94,109,153],"injection":[61,95],"focusing":[63],"solely":[64],"single-node":[66],"misclassification,":[67],"limits":[69],"their":[70,185],"practicality":[71],"real-world":[73,164],"deployments.":[74],"To":[75,128],"address":[76],"these":[77],"limitations,":[78],"we":[79,134],"propose":[80,135],"a":[81,92,107,112,136,150],"clean-label":[82],"attack":[85,177,209],"induces":[87],"one-hop":[88],"neighborhood":[89],"misclassification":[90],"under":[91,191],"minimal":[93],"budget.":[96],"Without":[97],"altering":[98],"target":[99,113,119,126,182],"nodes\u2019":[100],"features":[101],"or":[102],"labels,":[103],"our":[104,172],"method":[105],"attaches":[106],"single":[108],"node":[110,138],"node,":[114],"thereby":[115],"misclassifying":[116],"both":[117,181],"the":[118,125,197],"its":[121],"immediate":[122],"neighbors":[123,186],"as":[124],"class.":[127],"maximize":[129],"effectiveness":[130],"preserving":[132],"stealthiness,":[133],"poisoned":[137],"selection":[139],"strategy":[140],"guided":[141],"by":[142],"semantic":[143],"consistency":[144],"structural":[146],"activeness,":[147],"design":[149],"conditional":[151],"diffusion-based":[152],"generator":[154],"optimized":[155],"multiple":[157,163],"auxiliary":[158],"objectives.":[159],"Extensive":[160],"experiments":[161],"benchmarks":[165],"mainstream":[167],"GNN":[168],"architectures":[169],"show":[170],"approach":[173],"achieves":[174],"over":[175],"95%":[176],"rate":[179],"most":[188],"settings,":[189],"including":[190],"state-of-the-art":[192],"defenses.":[193],"These":[194],"findings":[195],"underscore":[196],"urgent":[198],"need":[199],"for":[200],"more":[201],"robust":[202],"learning":[204],"systems":[205],"novel":[208],"surfaces":[210],"security.":[213]},"counts_by_year":[],"updated_date":"2026-04-02T13:48:15.688549","created_date":"2026-03-28T00:00:00"}