{"id":"https://openalex.org/W4417308894","doi":"https://doi.org/10.1145/3770854.3780158","title":"Devil's Hand: Data Poisoning Attacks to Locally Private Graph Learning Protocols","display_name":"Devil's Hand: Data Poisoning Attacks to Locally Private Graph Learning Protocols","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W4417308894","doi":"https://doi.org/10.1145/3770854.3780158"},"language":"en","primary_location":{"id":"doi:10.1145/3770854.3780158","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3780158","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3770854.3780158","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113269092","display_name":"Longzhu He","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longzhu He","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-7842-6605","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063693227","display_name":"Chaozhuo Li","orcid":"https://orcid.org/0000-0002-8179-7503"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaozhuo Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8179-7503","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102841330","display_name":"Peng Tang","orcid":"https://orcid.org/0000-0003-1304-8401"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Tang","raw_affiliation_strings":["Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-1304-8401","affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318679","display_name":"Sun Li","orcid":"https://orcid.org/0000-0002-5695-3404"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Sun","raw_affiliation_strings":["Beijing University of Post and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4562-2279","affiliations":[{"raw_affiliation_string":"Beijing University of Post and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022808022","display_name":"Shengfa Su","orcid":"https://orcid.org/0000-0002-6429-0081"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]},{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sen Su","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China and Chongqing University of Posts and Telecommunications, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0003-4266-7527","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China and Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382","https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036357902","display_name":"Philip S. Yu","orcid":"https://orcid.org/0000-0002-3491-5968"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip S. Yu","raw_affiliation_strings":["University of Illinois Chicago, Chicago, Illinois, USA"],"raw_orcid":"https://orcid.org/0000-0002-3491-5968","affiliations":[{"raw_affiliation_string":"University of Illinois Chicago, Chicago, Illinois, USA","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.03643007,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"395","last_page":"406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.5667999982833862,"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":0.5667999982833862,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.39419999718666077,"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/T11719","display_name":"Data Quality and Management","score":0.003700000001117587,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/differential-privacy","display_name":"Differential privacy","score":0.6320000290870667},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5264999866485596},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5234000086784363},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.4668000042438507},{"id":"https://openalex.org/keywords/social-graph","display_name":"Social graph","score":0.45399999618530273},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3479999899864197},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.337799996137619}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791100025177002},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.6320000290870667},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.6046000123023987},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5264999866485596},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5234000086784363},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.4668000042438507},{"id":"https://openalex.org/C2777522414","wikidata":"https://www.wikidata.org/wiki/Q648457","display_name":"Social graph","level":3,"score":0.45399999618530273},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3693999946117401},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3479999899864197},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3386000096797943},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28949999809265137},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.2757999897003174},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27059999108314514},{"id":"https://openalex.org/C64339825","wikidata":"https://www.wikidata.org/wiki/Q722659","display_name":"Graph property","level":5,"score":0.2702000141143799},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.265500009059906},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2549999952316284},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C140547941","wikidata":"https://www.wikidata.org/wiki/Q7797194","display_name":"Threat model","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3770854.3780158","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3780158","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.09803","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.09803","pdf_url":"https://arxiv.org/pdf/2506.09803","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"},{"id":"doi:10.48550/arxiv.2506.09803","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.09803","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3770854.3780158","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3780158","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Graph":[0],"neural":[1],"networks":[2],"(GNNs)":[3],"have":[4,13,54,202],"achieved":[5],"significant":[6],"success":[7],"in":[8,31,75,117],"graph":[9,39,51,96,135,149,184],"representation":[10],"learning":[11,40,52,136,150],"and":[12,69,121,131,170,195],"been":[14,115,204],"applied":[15],"to":[16,106,164,175],"various":[17],"domains.":[18],"However,":[19],"many":[20],"real-world":[21],"graphs":[22],"contain":[23],"sensitive":[24],"personal":[25],"information,":[26],"such":[27,101],"as":[28],"user":[29],"profiles":[30],"social":[32],"networks,":[33],"raising":[34],"serious":[35],"privacy":[36,62,67,81],"concerns":[37],"when":[38],"is":[41,125,191],"performed":[42],"using":[43],"GNNs.":[44],"To":[45],"address":[46],"this":[47],"issue,":[48],"locally":[49,147],"private":[50,148,183],"protocols":[53,59,102],"gained":[55],"considerable":[56],"attention.":[57],"These":[58],"leverage":[60],"the":[61,70,129,141,158,176,180,189,211],"advantages":[63],"of":[64,72,133,182,188],"local":[65,85],"differential":[66],"(LDP)":[68],"effectiveness":[71,187,209],"GNN's":[73],"message-passing":[74],"calibrating":[76],"noisy":[77],"data,":[78],"offering":[79],"strict":[80],"guarantees":[82],"for":[83,95,127,213],"users'":[84],"data":[86,107,143,174],"while":[87],"maintaining":[88],"high":[89],"utility":[90,181],"(e.g.,":[91],"node":[92],"classification":[93],"accuracy)":[94],"learning.":[97,185],"Despite":[98],"these":[99,123,161],"advantages,":[100],"may":[103],"be":[104],"vulnerable":[105],"poisoning":[108,144],"attacks,":[109],"a":[110],"threat":[111],"that":[112],"has":[113],"not":[114],"considered":[116],"previous":[118],"research.":[119],"Identifying":[120],"addressing":[122],"threats":[124],"crucial":[126],"ensuring":[128],"robustness":[130],"security":[132],"privacy-preserving":[134],"frameworks.":[137],"This":[138],"work":[139],"introduces":[140],"first":[142],"attack":[145,190],"targeting":[146],"protocols.":[151],"The":[152,186],"attacker":[153],"injects":[154],"fake":[155,162],"users":[156,163],"into":[157],"protocol,":[159],"manipulates":[160],"establish":[165],"links":[166],"with":[167],"genuine":[168],"users,":[169],"sends":[171],"carefully":[172],"crafted":[173],"server,":[177],"ultimately":[178],"compromising":[179],"demonstrated":[192],"both":[193],"theoretically":[194],"empirically.":[196],"In":[197],"addition,":[198],"several":[199],"defense":[200],"strategies":[201],"also":[203],"explored,":[205],"but":[206],"their":[207],"limited":[208],"highlights":[210],"need":[212],"more":[214],"robust":[215],"defenses.":[216]},"counts_by_year":[],"updated_date":"2026-08-02T14:50:37.381335","created_date":"2025-10-10T00:00:00"}