{"id":"https://openalex.org/W7163993060","doi":"https://doi.org/10.48550/arxiv.2606.08067","title":"Beyond Homophily: Towards Generalized Graph Reconstruction Attack and Defense","display_name":"Beyond Homophily: Towards Generalized Graph Reconstruction Attack and Defense","publication_year":2026,"publication_date":"2026-06-06","ids":{"openalex":"https://openalex.org/W7163993060","doi":"https://doi.org/10.48550/arxiv.2606.08067"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.08067","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08067","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.08067","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138246382","display_name":"Zhanke Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Zhanke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138229232","display_name":"Bo Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138239400","display_name":"Xuan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138239493","display_name":"Jiangchao Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Jiangchao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138203606","display_name":"Sanmi Koyejo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koyejo, Sanmi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138209625","display_name":"Michael K. Ng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ng, Michael K.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.0010999999940395355,"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":0.0007999999797903001,"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/adjacency-list","display_name":"Adjacency list","score":0.6381000280380249},{"id":"https://openalex.org/keywords/adjacency-matrix","display_name":"Adjacency matrix","score":0.5759000182151794},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.545799970626831},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4837000072002411},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.42649999260902405},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.40400001406669617},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.35089999437332153}],"concepts":[{"id":"https://openalex.org/C110484373","wikidata":"https://www.wikidata.org/wiki/Q264398","display_name":"Adjacency list","level":2,"score":0.6381000280380249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6273999810218811},{"id":"https://openalex.org/C180356752","wikidata":"https://www.wikidata.org/wiki/Q727035","display_name":"Adjacency matrix","level":3,"score":0.5759000182151794},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.545799970626831},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5078999996185303},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4837000072002411},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.42649999260902405},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.40400001406669617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38339999318122864},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3296000063419342},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3158000111579895},{"id":"https://openalex.org/C35525427","wikidata":"https://www.wikidata.org/wiki/Q745881","display_name":"Intrusion detection system","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30250000953674316},{"id":"https://openalex.org/C2777522414","wikidata":"https://www.wikidata.org/wiki/Q648457","display_name":"Social graph","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C159246509","wikidata":"https://www.wikidata.org/wiki/Q5428725","display_name":"Factor graph","level":3,"score":0.26809999346733093},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C64339825","wikidata":"https://www.wikidata.org/wiki/Q722659","display_name":"Graph property","level":5,"score":0.26269999146461487},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C106937863","wikidata":"https://www.wikidata.org/wiki/Q7236518","display_name":"Power graph analysis","level":3,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.08067","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08067","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:10.48550/arxiv.2606.08067","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08067","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4992852807044983,"display_name":"Reduced inequalities"}],"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],"are":[4],"widely":[5],"deployed":[6],"on":[7,113],"relational":[8],"data,":[9],"yet":[10],"they":[11],"can":[12],"leak":[13],"sensitive":[14],"or":[15],"proprietary":[16],"information":[17,164],"about":[18],"the":[19,43,83,102,124,133,147,154,166],"training":[20,44],"graph":[21,32,79,182],"adjacency,":[22],"e.g.,":[23],"social":[24],"ties,":[25],"transactions,":[26],"and":[27,64,73,82,120,184],"interactions.":[28],"This":[29],"work":[30],"studies":[31],"reconstruction":[33,191,200],"attacks":[34,189],"(GRA),":[35],"a":[36,47,59,96,107,137,176],"form":[37],"of":[38,53,62,109,146],"model":[39,149],"inversion":[40],"that":[41,187],"reconstructs":[42,132],"adjacency":[45,66,134,139],"from":[46],"trained":[48],"GNN,":[49],"given":[50],"different":[51],"levels":[52],"attacker-side":[54],"information.":[55],"We":[56],"first":[57],"provide":[58],"systematic":[60],"characterization":[61],"when":[63],"why":[65],"becomes":[67],"recoverable":[68],"through":[69,95],"features,":[70],"labels,":[71],"embeddings,":[72],"predictions,":[74],"with":[75,144,202],"leakage":[76],"modulated":[77],"by":[78,88,135],"homophily,":[80],"heterophily,":[81],"model's":[84],"inductive":[85],"bias.":[86],"Motivated":[87],"these":[89],"findings,":[90],"we":[91,116,127,157],"view":[92],"GNN":[93],"inference":[94],"Markov":[97],"chain":[98,108,168],"approximation":[99],"lens,":[100],"treating":[101],"layered":[103],"forward":[104],"computation":[105],"as":[106],"topology-dependent":[110],"representations.":[111],"Building":[112],"this":[114],"view,":[115],"develop":[117],"complementary":[118],"attack":[119,125],"defense":[121,155],"methods.":[122],"On":[123,153],"side,":[126,156],"propose":[128,158],"MC-GRA":[129],"(+),":[130,160],"which":[131,161],"optimizing":[136],"surrogate":[138],"whose":[140],"GNN-induced":[141],"representations":[142],"align":[143],"those":[145],"target":[148],"at":[150],"each":[151],"layer.":[152],"MC-GPB":[159],"suppresses":[162],"adjacency-dependent":[163],"throughout":[165],"representation":[167],"while":[169,196],"aiming":[170],"to":[171],"preserve":[172],"classification":[173],"accuracy":[174,205],"under":[175],"privacy-utility":[177],"trade-off.":[178],"Experiments":[179],"across":[180],"homophilic/heterophilic":[181],"benchmarks":[183],"GNNs":[185],"show":[186],"our":[188,197],"improve":[190],"fidelity":[192],"over":[193],"prior":[194],"methods,":[195],"defenses":[198],"reduce":[199],"success":[201],"only":[203],"minor":[204],"loss.":[206]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-10T00:00:00"}