{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LSFQRXRJCADUFES5AI7X26BCXS","short_pith_number":"pith:LSFQRXRJ","schema_version":"1.0","canonical_sha256":"5c8b08de29100742925d023f7d7822bcbeafcbda0c41e4ec74366664f26e4d42","source":{"kind":"arxiv","id":"2102.05429","version":1},"attestation_state":"computed","paper":{"title":"Node-Level Membership Inference Attacks Against Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Michael Backes, Rui Wen, Xinlei He, Yang Zhang, Yixin Wu, Yun Shen","submitted_at":"2021-02-10T13:51:54Z","abstract_excerpt":"Many real-world data comes in the form of graphs, such as social networks and protein structure. To fully utilize the information contained in graph data, a new family of machine learning (ML) models, namely graph neural networks (GNNs), has been introduced. Previous studies have shown that machine learning models are vulnerable to privacy attacks. However, most of the current efforts concentrate on ML models trained on data from the Euclidean space, like images and texts. On the other hand, privacy risks stemming from GNNs remain largely unstudied.\n  In this paper, we fill the gap by performi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2102.05429","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2021-02-10T13:51:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7a23d7376e9e8638dc5e09fd6d2ae6820b3ac4da2f6f26171fd44528d6f42b8b","abstract_canon_sha256":"92fd05c797ac03b4a0579553912fc86ce413832d4263194160436e318a4179ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:18.542254Z","signature_b64":"h3SictwMOYtNjQODheBWhJuPvfxrRcI+BfdwWNUeAviPPke3/RPwKJuCJ9Y0AjlwDPmXUdwjPArJe86/I03OBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c8b08de29100742925d023f7d7822bcbeafcbda0c41e4ec74366664f26e4d42","last_reissued_at":"2026-07-05T02:14:18.541780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:18.541780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Node-Level Membership Inference Attacks Against Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Michael Backes, Rui Wen, Xinlei He, Yang Zhang, Yixin Wu, Yun Shen","submitted_at":"2021-02-10T13:51:54Z","abstract_excerpt":"Many real-world data comes in the form of graphs, such as social networks and protein structure. To fully utilize the information contained in graph data, a new family of machine learning (ML) models, namely graph neural networks (GNNs), has been introduced. Previous studies have shown that machine learning models are vulnerable to privacy attacks. However, most of the current efforts concentrate on ML models trained on data from the Euclidean space, like images and texts. On the other hand, privacy risks stemming from GNNs remain largely unstudied.\n  In this paper, we fill the gap by performi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.05429","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2102.05429/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2102.05429","created_at":"2026-07-05T02:14:18.541833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.05429v1","created_at":"2026-07-05T02:14:18.541833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.05429","created_at":"2026-07-05T02:14:18.541833+00:00"},{"alias_kind":"pith_short_12","alias_value":"LSFQRXRJCADU","created_at":"2026-07-05T02:14:18.541833+00:00"},{"alias_kind":"pith_short_16","alias_value":"LSFQRXRJCADUFES5","created_at":"2026-07-05T02:14:18.541833+00:00"},{"alias_kind":"pith_short_8","alias_value":"LSFQRXRJ","created_at":"2026-07-05T02:14:18.541833+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04069","citing_title":"Bayesian Membership Privacy for Graph Neural Networks","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06423","citing_title":"Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LSFQRXRJCADUFES5AI7X26BCXS","json":"https://pith.science/pith/LSFQRXRJCADUFES5AI7X26BCXS.json","graph_json":"https://pith.science/api/pith-number/LSFQRXRJCADUFES5AI7X26BCXS/graph.json","events_json":"https://pith.science/api/pith-number/LSFQRXRJCADUFES5AI7X26BCXS/events.json","paper":"https://pith.science/paper/LSFQRXRJ"},"agent_actions":{"view_html":"https://pith.science/pith/LSFQRXRJCADUFES5AI7X26BCXS","download_json":"https://pith.science/pith/LSFQRXRJCADUFES5AI7X26BCXS.json","view_paper":"https://pith.science/paper/LSFQRXRJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.05429&json=true","fetch_graph":"https://pith.science/api/pith-number/LSFQRXRJCADUFES5AI7X26BCXS/graph.json","fetch_events":"https://pith.science/api/pith-number/LSFQRXRJCADUFES5AI7X26BCXS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LSFQRXRJCADUFES5AI7X26BCXS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LSFQRXRJCADUFES5AI7X26BCXS/action/storage_attestation","attest_author":"https://pith.science/pith/LSFQRXRJCADUFES5AI7X26BCXS/action/author_attestation","sign_citation":"https://pith.science/pith/LSFQRXRJCADUFES5AI7X26BCXS/action/citation_signature","submit_replication":"https://pith.science/pith/LSFQRXRJCADUFES5AI7X26BCXS/action/replication_record"}},"created_at":"2026-07-05T02:14:18.541833+00:00","updated_at":"2026-07-05T02:14:18.541833+00:00"}