{"id":"https://openalex.org/W4412876837","doi":"https://doi.org/10.1145/3711896.3737179","title":"Verification of Incomplete Graph Unlearning through Adversarial Perturbations","display_name":"Verification of Incomplete Graph Unlearning through Adversarial Perturbations","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412876837","doi":"https://doi.org/10.1145/3711896.3737179"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3737179","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737179","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737179","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737179","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101898735","display_name":"Kun Wu","orcid":"https://orcid.org/0009-0009-9954-0886"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kun Wu","raw_affiliation_strings":["Stevens Institute of Technology, Hoboken, New Jersey, USA"],"raw_orcid":"https://orcid.org/0009-0009-9954-0886","affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology, Hoboken, New Jersey, USA","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100460778","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0002-3913-815X"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wendy Hui Wang","raw_affiliation_strings":["Stevens Institute of Technology, Hoboken, New Jersey, USA"],"raw_orcid":"https://orcid.org/0000-0002-3913-815X","affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology, Hoboken, New Jersey, USA","institution_ids":["https://openalex.org/I108468826"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I108468826"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3204","last_page":"3215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9979000091552734,"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":0.9979000091552734,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9932000041007996,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.98580002784729,"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/adversarial-system","display_name":"Adversarial system","score":0.7689403295516968},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.693150520324707},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44762158393859863},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.42042112350463867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35835856199264526}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7689403295516968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.693150520324707},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44762158393859863},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42042112350463867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35835856199264526}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711896.3737179","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737179","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737179","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3711896.3737179","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737179","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737179","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[{"id":"https://openalex.org/G2213108233","display_name":"SaTC: CORE: Small: Securing Network Embedding against Privacy Attacks","funder_award_id":"2135988","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2280051180","display_name":null,"funder_award_id":"CNS-2029038, CNS-2135988","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G7664103396","display_name":"SaTC: CORE: Medium: Privacy for All: Ensuring Fair Privacy Protection in Machine Learning","funder_award_id":"2029038","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/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412876837.pdf","grobid_xml":"https://content.openalex.org/works/W4412876837.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2048881327","https://openalex.org/W2294710185","https://openalex.org/W2752929869","https://openalex.org/W2770885069","https://openalex.org/W2795807997","https://openalex.org/W2803831897","https://openalex.org/W2908442265","https://openalex.org/W2912083425","https://openalex.org/W2951823788","https://openalex.org/W2964583308","https://openalex.org/W2964971928","https://openalex.org/W2984488829","https://openalex.org/W2997404190","https://openalex.org/W3007657110","https://openalex.org/W3026865739","https://openalex.org/W3081325717","https://openalex.org/W3094504436","https://openalex.org/W3098276446","https://openalex.org/W3106390645","https://openalex.org/W3124962940","https://openalex.org/W3154155772","https://openalex.org/W3160274714","https://openalex.org/W3174532363","https://openalex.org/W4206078729","https://openalex.org/W4286256876","https://openalex.org/W4296562799","https://openalex.org/W4318815354","https://openalex.org/W4362706499","https://openalex.org/W4378966525","https://openalex.org/W4385568427","https://openalex.org/W4387986864","https://openalex.org/W4391326578","https://openalex.org/W4393147268","https://openalex.org/W4393252682","https://openalex.org/W4396843900","https://openalex.org/W4396844349","https://openalex.org/W4410609060","https://openalex.org/W4412876837","https://openalex.org/W6757925611","https://openalex.org/W6782272117"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492"],"abstract_inverted_index":{"Graph":[0,13],"unlearning":[1,26,210,218],"(GU)":[2],"enables":[3],"data":[4,9],"owners":[5],"to":[6,69,94,101,175],"remove":[7],"specific":[8,33],"from":[10,56,123],"a":[11,18,32,50,76,88,119,172,212],"trained":[12,58],"Neural":[14],"Network":[15],"(GNN).":[16],"However,":[17],"dishonest":[19],"model":[20,46,100,126,160],"provider":[21,47,161],"may":[22],"cheat":[23],"on":[24,31],"the":[25,45,53,57,63,84,99,103,112,124,130,137,140,145,148,152,156,159,177,189,200],"process.":[27],"This":[28],"paper":[29],"focuses":[30],"type":[34],"of":[35,52,78,90,105,111,121,139,204,214],"cheating":[36,72],"behavior":[37],"in":[38,83,147,164,206],"GU,":[39],"namely":[40],"incomplete":[41,165,208],"edge":[42,209],"unlearning,":[43],"where":[44],"removes":[48],"only":[49,118],"subset":[51,120],"requested":[54],"edges":[55,114,142],"GNN.":[59],"We":[60,186],"introduce":[61],"PANDA,":[62,169],"first":[64],"probabilistic":[65],"GU":[66],"verification":[67,190],"framework,":[68],"detect":[70],"such":[71],"behaviors.":[73],"PANDA":[74,205,224],"identifies":[75],"set":[77,89],"nodes,":[79,82],"called":[80],"token":[81,106,131,149,178],"graph,":[85],"and":[86,143,180,202,217,238],"injects":[87],"fake":[91],"edges,":[92,97],"referred":[93],"as":[95],"challenge":[96,113,141,184],"into":[98],"manipulate":[102],"predictions":[104],"nodes.":[107],"A":[108],"key":[109],"property":[110],"is":[115],"that":[116,158,223],"removing":[117],"them":[122],"poisoned":[125],"does":[127],"not":[128],"change":[129,146],"nodes'":[132,150],"prediction.":[133],"Then":[134],"by":[135,193],"requesting":[136],"removal":[138],"observing":[144],"predictions,":[151],"verifier":[153],"can":[154],"assess":[155],"likelihood":[157],"has":[162],"engaged":[163],"unlearning.":[166],"To":[167],"develop":[168],"we":[170,221],"design":[171],"novel":[173],"algorithm":[174],"identify":[176],"nodes":[179],"generate":[181],"their":[182],"associated":[183],"edges.":[185],"rigorously":[187],"quantify":[188],"probabilities":[191],"achieved":[192],"PANDA.":[194],"Our":[195,236],"extensive":[196],"empirical":[197],"studies":[198],"demonstrate":[199],"efficiency":[201],"effectiveness":[203],"detecting":[207],"across":[211],"variety":[213],"GNN":[215],"models":[216],"algorithms.":[219],"Furthermore,":[220],"show":[222],"exhibits":[225],"strong":[226],"robustness":[227],"against":[228],"state-of-the-art":[229],"detection":[230],"methods":[231],"for":[232],"graph":[233],"adversarial":[234],"perturbations.":[235],"code":[237],"datasets":[239],"are":[240],"available":[241],"at":[242],"https://github.com/kunwu522/unlearning-verification-gnn.":[243]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}