{"id":"https://openalex.org/W4400382067","doi":"https://doi.org/10.56553/popets-2024-0116","title":"Subgraph Structure Membership Inference Attacks against Graph Neural Networks","display_name":"Subgraph Structure Membership Inference Attacks against Graph Neural Networks","publication_year":2024,"publication_date":"2024-07-06","ids":{"openalex":"https://openalex.org/W4400382067","doi":"https://doi.org/10.56553/popets-2024-0116"},"language":"en","primary_location":{"id":"doi:10.56553/popets-2024-0116","is_oa":true,"landing_page_url":"https://doi.org/10.56553/popets-2024-0116","pdf_url":"https://petsymposium.org/popets/2024/popets-2024-0116.pdf","source":{"id":"https://openalex.org/S4210183172","display_name":"Proceedings on Privacy Enhancing Technologies","issn_l":"2299-0984","issn":["2299-0984"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320322","host_organization_name":"De Gruyter Open","host_organization_lineage":["https://openalex.org/P4310320322","https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter Open","De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings on Privacy Enhancing Technologies","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://petsymposium.org/popets/2024/popets-2024-0116.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041953281","display_name":"Xiuling Wang","orcid":"https://orcid.org/0009-0001-7681-7127"},"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":"Xiuling Wang","raw_affiliation_strings":["Stevens Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology","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":0.2778,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59768522,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"2024","issue":"4","first_page":"268","last_page":"290"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9925000071525574,"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":0.9925000071525574,"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/inference","display_name":"Inference","score":0.6420128345489502},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5566883683204651},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.511562168598175},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4778699278831482},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43647027015686035},{"id":"https://openalex.org/keywords/induced-subgraph-isomorphism-problem","display_name":"Induced subgraph isomorphism problem","score":0.4287306070327759},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3661876916885376},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.326699435710907},{"id":"https://openalex.org/keywords/voltage-graph","display_name":"Voltage graph","score":0.11704105138778687},{"id":"https://openalex.org/keywords/line-graph","display_name":"Line graph","score":0.10894197225570679}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6420128345489502},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5566883683204651},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.511562168598175},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4778699278831482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43647027015686035},{"id":"https://openalex.org/C191241153","wikidata":"https://www.wikidata.org/wiki/Q6027240","display_name":"Induced subgraph isomorphism problem","level":5,"score":0.4287306070327759},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3661876916885376},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.326699435710907},{"id":"https://openalex.org/C22149727","wikidata":"https://www.wikidata.org/wiki/Q7940747","display_name":"Voltage graph","level":4,"score":0.11704105138778687},{"id":"https://openalex.org/C203776342","wikidata":"https://www.wikidata.org/wiki/Q1378376","display_name":"Line graph","level":3,"score":0.10894197225570679}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.56553/popets-2024-0116","is_oa":true,"landing_page_url":"https://doi.org/10.56553/popets-2024-0116","pdf_url":"https://petsymposium.org/popets/2024/popets-2024-0116.pdf","source":{"id":"https://openalex.org/S4210183172","display_name":"Proceedings on Privacy Enhancing Technologies","issn_l":"2299-0984","issn":["2299-0984"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320322","host_organization_name":"De Gruyter Open","host_organization_lineage":["https://openalex.org/P4310320322","https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter Open","De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings on Privacy Enhancing Technologies","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.56553/popets-2024-0116","is_oa":true,"landing_page_url":"https://doi.org/10.56553/popets-2024-0116","pdf_url":"https://petsymposium.org/popets/2024/popets-2024-0116.pdf","source":{"id":"https://openalex.org/S4210183172","display_name":"Proceedings on Privacy Enhancing Technologies","issn_l":"2299-0984","issn":["2299-0984"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320322","host_organization_name":"De Gruyter Open","host_organization_lineage":["https://openalex.org/P4310320322","https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter Open","De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings on Privacy Enhancing Technologies","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5799999833106995}],"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/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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400382067.pdf","grobid_xml":"https://content.openalex.org/works/W4400382067.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W231720905","https://openalex.org/W1482551403","https://openalex.org/W2532922352","https://openalex.org/W2128390795","https://openalex.org/W2915540008","https://openalex.org/W2604893261","https://openalex.org/W3002471523","https://openalex.org/W2604114816","https://openalex.org/W2361654510","https://openalex.org/W2393701947"],"abstract_inverted_index":{"Graph":[0],"Neural":[1],"Networks":[2],"(GNNs)":[3],"have":[4,17,49,224],"been":[5],"widely":[6],"applied":[7],"to":[8,23,31,82,91,186,200,272],"various":[9],"applications":[10],"across":[11],"different":[12],"domains.":[13],"However,":[14],"recent":[15],"studies":[16],"shown":[18],"that":[19,119,166,178,197,223,236,250],"GNNs":[20],"are":[21],"susceptible":[22],"the":[24,41,53,61,74,105,121,126,148,176,180,188,201,206,211,220,225,229,237,265,268,273],"membership":[25,54,70,183],"inference":[26,71,149,184],"attacks":[27,118,169,185],"(MIAs)":[28],"which":[29,80],"aim":[30],"infer":[32,187],"if":[33],"some":[34],"particular":[35,93],"data":[36],"samples":[37],"were":[38],"included":[39],"in":[40,140,146],"model\u2019s":[42],"training":[43,62,107,135],"data.":[44],"While":[45],"most":[46],"previous":[47],"MIAs":[48],"focused":[50],"on":[51,228],"inferring":[52],"of":[55,69,88,155,240,267],"individual":[56],"nodes":[57,89],"and":[58,160,264],"edges":[59],"within":[60,104,219],"graph,":[63],"we":[64,113,192],"introduce":[65],"a":[66,85,92,98,101,136,194,258],"novel":[67,115],"form":[68],"attack":[72],"called":[73],"Structure":[75],"Membership":[76],"Inference":[77],"Attack":[78],"(SMIA)":[79],"aims":[81],"determine":[83],"whether":[84],"given":[86],"set":[87],"corresponds":[90],"target":[94,127,212,269],"structure,":[95],"such":[96],"as":[97],"clique":[99],"or":[100],"multi-hop":[102],"path,":[103],"original":[106],"graph.":[108],"To":[109],"address":[110],"this":[111],"issue,":[112],"present":[114],"black-box":[116],"SMIA":[117],"leverage":[120],"prediction":[122,208],"outputs":[123,209],"generated":[124],"by":[125,210],"GNN":[128,158],"model":[129,270],"for":[130],"inference.":[131],"Our":[132,151,214,232],"approach":[133,242],"involves":[134],"three-label":[137],"classifier,":[138],"which,":[139],"combination":[141],"with":[142,245],"shadow":[143],"training,":[144],"aids":[145],"enabling":[147],"attack.":[150],"extensive":[152],"experimental":[153],"evaluation":[154],"three":[156,161,172],"representative":[157],"models":[159],"real-world":[162],"graph":[163],"datasets":[164],"demonstrates":[165],"our":[167,241,255],"proposed":[168],"consistently":[170],"outperform":[171],"baseline":[173],"methods,":[174],"including":[175],"one":[177],"employs":[179],"conventional":[181],"link":[182],"subgraph":[189],"structure.":[190],"Additionally,":[191],"design":[193],"defense":[195,215,238,248,262,276],"mechanism":[196],"introduces":[198],"perturbations":[199],"node":[202,221],"embeddings":[203,222],"thus":[204],"influencing":[205],"corresponding":[207],"model.":[213],"selectively":[216],"perturbs":[217],"dimensions":[218],"least":[226],"impact":[227],"model's":[230],"accuracy.":[231],"empirical":[233],"results":[234],"demonstrate":[235],"effectiveness":[239],"is":[243],"comparable":[244],"two":[246,274],"established":[247],"techniques":[249],"employ":[251],"differential":[252],"privacy.":[253],"Moreover,":[254],"method":[256],"achieves":[257],"better":[259],"trade-off":[260],"between":[261],"strength":[263],"accuracy":[266],"compared":[271],"existing":[275],"methods.":[277]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}