{"id":"https://openalex.org/W4308642595","doi":"https://doi.org/10.1145/3548606.3560662","title":"Group Property Inference Attacks Against Graph Neural Networks","display_name":"Group Property Inference Attacks Against Graph Neural Networks","publication_year":2022,"publication_date":"2022-11-07","ids":{"openalex":"https://openalex.org/W4308642595","doi":"https://doi.org/10.1145/3548606.3560662"},"language":"en","primary_location":{"id":"doi:10.1145/3548606.3560662","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3548606.3560662","pdf_url":null,"source":{"id":"https://openalex.org/S4363608815","display_name":"Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security","raw_type":"proceedings-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":"https://openalex.org/A5100771708","display_name":"Xiuling Wang","orcid":"https://orcid.org/0000-0003-4690-1341"},"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":true,"raw_author_name":"Xiuling Wang","raw_affiliation_strings":["Stevens Institute of Technology, Hoboken, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology, Hoboken, NJ, 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, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology, Hoboken, NJ, USA","institution_ids":["https://openalex.org/I108468826"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100771708"],"corresponding_institution_ids":["https://openalex.org/I108468826"],"apc_list":null,"apc_paid":null,"fwci":3.235,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.93534711,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2871","last_page":"2884"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9998000264167786,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9998000264167786,"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":0.9991000294685364,"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":0.989799976348877,"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/computer-science","display_name":"Computer science","score":0.7241823673248291},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.7148891687393188},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6492474675178528},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.5877326130867004},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5418641567230225},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.466940313577652},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.423225462436676},{"id":"https://openalex.org/keywords/attack-model","display_name":"Attack model","score":0.4230678677558899},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4134003818035126},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40782248973846436},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3642065227031708},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.2430206537246704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7241823673248291},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.7148891687393188},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6492474675178528},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5877326130867004},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5418641567230225},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.466940313577652},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.423225462436676},{"id":"https://openalex.org/C65856478","wikidata":"https://www.wikidata.org/wiki/Q3991682","display_name":"Attack model","level":2,"score":0.4230678677558899},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4134003818035126},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40782248973846436},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3642065227031708},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2430206537246704},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3548606.3560662","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3548606.3560662","pdf_url":null,"source":{"id":"https://openalex.org/S4363608815","display_name":"Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.5099999904632568},{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1473189865","https://openalex.org/W1979104937","https://openalex.org/W2051267297","https://openalex.org/W2112796928","https://openalex.org/W2138358979","https://openalex.org/W2160692033","https://openalex.org/W2473418344","https://openalex.org/W2512472178","https://openalex.org/W2519887557","https://openalex.org/W2535690855","https://openalex.org/W2597603852","https://openalex.org/W2624431344","https://openalex.org/W2768375068","https://openalex.org/W2884943453","https://openalex.org/W2897830718","https://openalex.org/W2914982603","https://openalex.org/W2962835266","https://openalex.org/W2963456518","https://openalex.org/W2964162474","https://openalex.org/W3035261884","https://openalex.org/W3035523484","https://openalex.org/W3091473186","https://openalex.org/W3094559034","https://openalex.org/W3096738375","https://openalex.org/W3153329411","https://openalex.org/W3157327836","https://openalex.org/W3171497996","https://openalex.org/W3189551349","https://openalex.org/W3196012972","https://openalex.org/W3200345107","https://openalex.org/W3213807399","https://openalex.org/W4230974672","https://openalex.org/W6776644305","https://openalex.org/W6801935883","https://openalex.org/W6807593720"],"related_works":["https://openalex.org/W4388150944","https://openalex.org/W4242235492","https://openalex.org/W4237162029","https://openalex.org/W2367268135","https://openalex.org/W4214858327","https://openalex.org/W2604394466","https://openalex.org/W2952603690","https://openalex.org/W4387796593","https://openalex.org/W2941205169","https://openalex.org/W4328053081"],"abstract_inverted_index":{"Recent":[0],"research":[1],"has":[2,66],"shown":[3],"that":[4,14,94,170,177,226],"machine":[5],"learning":[6],"(ML)":[7],"models":[8,129,159],"are":[9,79,107],"vulnerable":[10],"to":[11,60,82,172,204],"privacy":[12,41],"attacks":[13,92,140,151],"leak":[15],"information":[16],"about":[17],"the":[18,31,50,54,58,63,80,88,96,119,147,167,178,183,188,202,206,209,220],"training":[19,55,120],"data.":[20],"In":[21],"this":[22],"work,":[23],"we":[24,78,123,145,165,212],"consider":[25,124],"Graph":[26],"Neural":[27],"Networks":[28],"(GNNs)":[29],"as":[30],"target":[32,189],"model,":[33],"and":[34,75,103,136,160,175,223],"focus":[35],"on":[36,155,182,237],"a":[37,84,125,214],"particular":[38,99],"type":[39],"of":[40,53,87,98,101,127,133,149,208,216],"attack":[42,46,231],"named":[43],"property":[44,90,190],"inference":[45,91],"(PIA)":[47],"which":[48,200],"infers":[49],"sensitive":[51],"properties":[52,71],"graph":[56,76],"through":[57,152],"access":[59],"GNNs.":[61],"While":[62],"existing":[64],"work":[65],"investigated":[67],"PIAs":[68],"against":[69,219],"graph-level":[70],"(e.g.,":[72,105],"node":[73],"degree":[74],"density),":[77],"first":[81],"perform":[83],"systematic":[85],"study":[86],"group":[89],"(GPIAs)":[93],"infer":[95,205],"distribution":[97],"groups":[100],"nodes":[102,112],"links":[104,109],"there":[106],"more":[108],"between":[110,115],"male":[111],"than":[113],"those":[114],"female":[116],"nodes)":[117],"in":[118,194],"graph.":[121],"First,":[122],"taxonomy":[126],"threat":[128],"with":[130,185,234],"various":[131],"types":[132],"adversary":[134,203],"knowledge,":[135],"design":[137,213],"six":[138],"different":[139],"for":[141],"these":[142,150,227],"settings.":[143],"Second,":[144],"demonstrate":[146,224],"effectiveness":[148],"extensive":[153],"experiments":[154],"three":[156,161],"representative":[157],"GNN":[158,179,238],"real-world":[162],"graphs.":[163],"Third,":[164],"analyze":[166],"underlying":[168],"factors":[169],"contribute":[171],"GPIA's":[173],"success,":[174],"show":[176],"model":[180,195,198,239],"trained":[181],"graphs":[184],"or":[186],"without":[187],"represents":[191],"some":[192],"dissimilarity":[193],"parameters":[196],"and/or":[197],"outputs,":[199],"enables":[201],"existence":[207],"property.":[210],"Further,":[211],"set":[215],"defense":[217],"mechanisms":[218,228],"GPIA":[221],"attacks,":[222],"empirically":[225],"can":[229],"reduce":[230],"accuracy":[232],"effectively":[233],"small":[235],"loss":[236],"accuracy.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}