{"id":"https://openalex.org/W4323066547","doi":"https://doi.org/10.1145/3543507.3583392","title":"Unnoticeable Backdoor Attacks on Graph Neural Networks","display_name":"Unnoticeable Backdoor Attacks on Graph Neural Networks","publication_year":2023,"publication_date":"2023-04-26","ids":{"openalex":"https://openalex.org/W4323066547","doi":"https://doi.org/10.1145/3543507.3583392"},"language":"en","primary_location":{"id":"doi:10.1145/3543507.3583392","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543507.3583392","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543507.3583392","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3543507.3583392","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091395218","display_name":"Enyan Dai","orcid":"https://orcid.org/0000-0001-9715-0280"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Enyan Dai","raw_affiliation_strings":["Pennsylvania State University, USA"],"raw_orcid":"https://orcid.org/0000-0001-9715-0280","affiliations":[{"raw_affiliation_string":"Pennsylvania State University, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039804358","display_name":"Minhua Lin","orcid":"https://orcid.org/0000-0003-1591-7172"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minhua Lin","raw_affiliation_strings":["Pennsylvania State University, USA"],"raw_orcid":"https://orcid.org/0000-0003-1591-7172","affiliations":[{"raw_affiliation_string":"Pennsylvania State University, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060725887","display_name":"X. D. Zhang","orcid":"https://orcid.org/0000-0003-0940-6595"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang Zhang","raw_affiliation_strings":["Pennsylvania State University, USA"],"raw_orcid":"https://orcid.org/0000-0003-0940-6595","affiliations":[{"raw_affiliation_string":"Pennsylvania State University, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011048500","display_name":"Suhang Wang","orcid":"https://orcid.org/0000-0003-3448-4878"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suhang Wang","raw_affiliation_strings":["Pennsylvania State University, USA"],"raw_orcid":"https://orcid.org/0000-0003-3448-4878","affiliations":[{"raw_affiliation_string":"Pennsylvania State University, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":15.104,"has_fulltext":true,"cited_by_count":70,"citation_normalized_percentile":{"value":0.9936651,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2263","last_page":"2273"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9936000108718872,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9451000094413757,"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/backdoor","display_name":"Backdoor","score":0.9941530227661133},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6985788941383362},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5978307723999023},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.4399111270904541},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32322925329208374}],"concepts":[{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.9941530227661133},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6985788941383362},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5978307723999023},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.4399111270904541},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32322925329208374}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3543507.3583392","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543507.3583392","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543507.3583392","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2303.01263","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.01263","pdf_url":"https://arxiv.org/pdf/2303.01263","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3543507.3583392","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543507.3583392","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543507.3583392","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G125128811","display_name":null,"funder_award_id":"W911NF-2110198","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G7366345995","display_name":"III: Small: Collaborative Research: Effective Labeled Data Generation via Generative Adversarial Learning","funder_award_id":"1909702","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7405368409","display_name":"CAREER: Novel Approaches for Mining Large and Complex Networks","funder_award_id":"1707548","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306110","display_name":"U.S. Department of Homeland Security","ror":"https://ror.org/00jyr0d86"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4323066547.pdf","grobid_xml":"https://content.openalex.org/works/W4323066547.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2027482274","https://openalex.org/W2153959628","https://openalex.org/W2597603852","https://openalex.org/W2604763608","https://openalex.org/W2803831897","https://openalex.org/W2807021761","https://openalex.org/W2914953695","https://openalex.org/W2946297661","https://openalex.org/W2949208225","https://openalex.org/W2961295589","https://openalex.org/W2962711740","https://openalex.org/W2964015378","https://openalex.org/W2964283260","https://openalex.org/W2964971928","https://openalex.org/W2966149470","https://openalex.org/W2972317931","https://openalex.org/W2997404190","https://openalex.org/W3012846134","https://openalex.org/W3033100793","https://openalex.org/W3034492151","https://openalex.org/W3035237749","https://openalex.org/W3036446966","https://openalex.org/W3085985940","https://openalex.org/W3098276446","https://openalex.org/W3099064659","https://openalex.org/W3099152386","https://openalex.org/W3100078588","https://openalex.org/W3100848837","https://openalex.org/W3110933132","https://openalex.org/W3117178429","https://openalex.org/W3122063025","https://openalex.org/W3136543599","https://openalex.org/W3167334189","https://openalex.org/W3168561516","https://openalex.org/W3171723757","https://openalex.org/W3172780638","https://openalex.org/W3198375173","https://openalex.org/W3206020630","https://openalex.org/W3207981989","https://openalex.org/W3215430231","https://openalex.org/W4206352019","https://openalex.org/W4212890525","https://openalex.org/W4224298369","https://openalex.org/W4225810510","https://openalex.org/W4285723986","https://openalex.org/W4287020250","https://openalex.org/W4288064365","https://openalex.org/W4294558607","https://openalex.org/W4295262505","https://openalex.org/W4308265477","https://openalex.org/W4318812135"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4320031223","https://openalex.org/W4200629851","https://openalex.org/W4281902577","https://openalex.org/W4309417370","https://openalex.org/W4292107232","https://openalex.org/W3009072493","https://openalex.org/W4401407399"],"abstract_inverted_index":{"Graph":[0],"Neural":[1],"Networks":[2],"(GNNs)":[3],"have":[4],"achieved":[5],"promising":[6],"results":[7],"in":[8,59,92,123,160,196],"various":[9,186],"tasks":[10],"such":[11],"as":[12],"node":[13],"classification":[14],"and":[15,49,112,120,156],"graph":[16,45,70,93,133],"classification.":[17],"Recent":[18],"studies":[19],"find":[20],"that":[21,100,174],"GNNs":[22,65],"are":[23,34,88,175],"vulnerable":[24],"to":[25,54,75,79,148,153,170,177],"adversarial":[26],"attacks.":[27,201],"However,":[28],"effective":[29,109,172,198],"backdoor":[30,41,94,110,134,200],"attacks":[31,111,135],"on":[32,67,182],"graphs":[33],"still":[35],"an":[36],"open":[37],"problem.":[38],"In":[39],"particular,":[40],"attack":[42,106,138,144],"poisons":[43],"the":[44,50,60,68,113,143,151,161,190],"by":[46],"attaching":[47],"triggers":[48,115,155,173],"target":[51,80,157],"class":[52,81,158],"label":[53],"a":[55,104,128],"set":[56],"of":[57,131,192],"nodes":[58,78,152],"training":[61],"graph.":[62],"The":[63],"backdoored":[64],"trained":[66],"poisoned":[69],"will":[71],"then":[72],"be":[73,117,178],"misled":[74],"predict":[76],"test":[77],"once":[82],"attached":[83],"with":[84,136],"triggers.":[85],"Though":[86],"there":[87],"some":[89],"initial":[90],"efforts":[91],"attacks,":[95],"our":[96,193],"empirical":[97],"analysis":[98],"shows":[99],"they":[101],"may":[102],"require":[103],"large":[105],"budget":[107],"for":[108],"injected":[114],"can":[116],"easily":[118],"detected":[119],"pruned.":[121],"Therefore,":[122],"this":[124],"paper,":[125],"we":[126,146],"study":[127],"novel":[129],"problem":[130],"unnoticeable":[132,199],"limited":[137],"budget.":[139],"To":[140],"fully":[141],"utilize":[142],"budget,":[145],"propose":[147],"deliberately":[149],"select":[150],"inject":[154],"labels":[159],"poisoning":[162],"phase.":[163],"An":[164],"adaptive":[165],"trigger":[166],"generator":[167],"is":[168],"deployed":[169],"obtain":[171],"difficult":[176],"noticed.":[179],"Extensive":[180],"experiments":[181],"real-world":[183],"datasets":[184],"against":[185],"defense":[187],"strategies":[188],"demonstrate":[189],"effectiveness":[191],"proposed":[194],"method":[195],"conducting":[197]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":39},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":2}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}