{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:E6LQFF6QM3PJSWPN73C35QRITA","short_pith_number":"pith:E6LQFF6Q","schema_version":"1.0","canonical_sha256":"27970297d066de9959edfec5bec2289824fb0cfe07cf962ab2abdd6176473ec4","source":{"kind":"arxiv","id":"2109.08907","version":2},"attestation_state":"computed","paper":{"title":"Releasing Graph Neural Networks with Differential Privacy Guarantees","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Iyiola E. Olatunji, Megha Khosla, Thorben Funke","submitted_at":"2021-09-18T11:35:19Z","abstract_excerpt":"With the increasing popularity of graph neural networks (GNNs) in several sensitive applications like healthcare and medicine, concerns have been raised over the privacy aspects of trained GNNs. More notably, GNNs are vulnerable to privacy attacks, such as membership inference attacks, even if only black-box access to the trained model is granted. We propose PrivGNN, a privacy-preserving framework for releasing GNN models in a centralized setting. Assuming an access to a public unlabeled graph, PrivGNN provides a framework to release GNN models trained explicitly on public data along with know"},"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":"2109.08907","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-18T11:35:19Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"076ccc13ab91d1c878f0586e8c01acc5a1f6a90bae99cc6fd4fe93418c9f5c4b","abstract_canon_sha256":"3cff4e87d1cd899861b7708532d6563ad913c6584fa9361c864f2492cac936e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:02.966455Z","signature_b64":"bp+swUGXeytYmPKWdJjmxBMc0+NG6cgvNadH2GEPbTDIblSgogFM4CDEu052RL56rlSGtH/hPAC7ieJ4Y4uvBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27970297d066de9959edfec5bec2289824fb0cfe07cf962ab2abdd6176473ec4","last_reissued_at":"2026-07-05T07:08:02.965999Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:02.965999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Releasing Graph Neural Networks with Differential Privacy Guarantees","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Iyiola E. Olatunji, Megha Khosla, Thorben Funke","submitted_at":"2021-09-18T11:35:19Z","abstract_excerpt":"With the increasing popularity of graph neural networks (GNNs) in several sensitive applications like healthcare and medicine, concerns have been raised over the privacy aspects of trained GNNs. More notably, GNNs are vulnerable to privacy attacks, such as membership inference attacks, even if only black-box access to the trained model is granted. We propose PrivGNN, a privacy-preserving framework for releasing GNN models in a centralized setting. Assuming an access to a public unlabeled graph, PrivGNN provides a framework to release GNN models trained explicitly on public data along with know"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.08907","kind":"arxiv","version":2},"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/2109.08907/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":"2109.08907","created_at":"2026-07-05T07:08:02.966056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.08907v2","created_at":"2026-07-05T07:08:02.966056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.08907","created_at":"2026-07-05T07:08:02.966056+00:00"},{"alias_kind":"pith_short_12","alias_value":"E6LQFF6QM3PJ","created_at":"2026-07-05T07:08:02.966056+00:00"},{"alias_kind":"pith_short_16","alias_value":"E6LQFF6QM3PJSWPN","created_at":"2026-07-05T07:08:02.966056+00:00"},{"alias_kind":"pith_short_8","alias_value":"E6LQFF6Q","created_at":"2026-07-05T07:08:02.966056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E6LQFF6QM3PJSWPN73C35QRITA","json":"https://pith.science/pith/E6LQFF6QM3PJSWPN73C35QRITA.json","graph_json":"https://pith.science/api/pith-number/E6LQFF6QM3PJSWPN73C35QRITA/graph.json","events_json":"https://pith.science/api/pith-number/E6LQFF6QM3PJSWPN73C35QRITA/events.json","paper":"https://pith.science/paper/E6LQFF6Q"},"agent_actions":{"view_html":"https://pith.science/pith/E6LQFF6QM3PJSWPN73C35QRITA","download_json":"https://pith.science/pith/E6LQFF6QM3PJSWPN73C35QRITA.json","view_paper":"https://pith.science/paper/E6LQFF6Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.08907&json=true","fetch_graph":"https://pith.science/api/pith-number/E6LQFF6QM3PJSWPN73C35QRITA/graph.json","fetch_events":"https://pith.science/api/pith-number/E6LQFF6QM3PJSWPN73C35QRITA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E6LQFF6QM3PJSWPN73C35QRITA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E6LQFF6QM3PJSWPN73C35QRITA/action/storage_attestation","attest_author":"https://pith.science/pith/E6LQFF6QM3PJSWPN73C35QRITA/action/author_attestation","sign_citation":"https://pith.science/pith/E6LQFF6QM3PJSWPN73C35QRITA/action/citation_signature","submit_replication":"https://pith.science/pith/E6LQFF6QM3PJSWPN73C35QRITA/action/replication_record"}},"created_at":"2026-07-05T07:08:02.966056+00:00","updated_at":"2026-07-05T07:08:02.966056+00:00"}