{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZRIUZIRUSV4MEFSGVG6YM3TOBY","short_pith_number":"pith:ZRIUZIRU","schema_version":"1.0","canonical_sha256":"cc514ca2349578c21646a9bd866e6e0e2eae68d54fbc68ad9db735bec13b69af","source":{"kind":"arxiv","id":"2203.09205","version":1},"attestation_state":"computed","paper":{"title":"SoK: Differential Privacy on Graph-Structured Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Daniel Rueckert, Dmitrii Usynin, Georgios Kaissis, Johannes C. Paetzold, Tamara T. Mueller","submitted_at":"2022-03-17T09:56:32Z","abstract_excerpt":"In this work, we study the applications of differential privacy (DP) in the context of graph-structured data. We discuss the formulations of DP applicable to the publication of graphs and their associated statistics as well as machine learning on graph-based data, including graph neural networks (GNNs). The formulation of DP in the context of graph-structured data is difficult, as individual data points are interconnected (often non-linearly or sparsely). This connectivity complicates the computation of individual privacy loss in differentially private learning. The problem is exacerbated by a"},"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":"2203.09205","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2022-03-17T09:56:32Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5daa7d1d80dd201a4ae47d26e3b8a0ed92a156bc80520886c055c974d96f5a3c","abstract_canon_sha256":"0d2c35829d97bfc795ad629e1db9c02450900a68be96958ffffc007066f438c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:08.788164Z","signature_b64":"L4L38uTy/6+O1nHrJajofLYGQPRJX3EFRM66uFzyLKDhQ/D5UfwGtQ3EDIMCw5/MW3rNTEiycBWVlWFrVFPCAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc514ca2349578c21646a9bd866e6e0e2eae68d54fbc68ad9db735bec13b69af","last_reissued_at":"2026-07-05T04:06:08.787528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:08.787528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SoK: Differential Privacy on Graph-Structured Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Daniel Rueckert, Dmitrii Usynin, Georgios Kaissis, Johannes C. Paetzold, Tamara T. Mueller","submitted_at":"2022-03-17T09:56:32Z","abstract_excerpt":"In this work, we study the applications of differential privacy (DP) in the context of graph-structured data. We discuss the formulations of DP applicable to the publication of graphs and their associated statistics as well as machine learning on graph-based data, including graph neural networks (GNNs). The formulation of DP in the context of graph-structured data is difficult, as individual data points are interconnected (often non-linearly or sparsely). This connectivity complicates the computation of individual privacy loss in differentially private learning. The problem is exacerbated by a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.09205","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/2203.09205/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":"2203.09205","created_at":"2026-07-05T04:06:08.787595+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.09205v1","created_at":"2026-07-05T04:06:08.787595+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.09205","created_at":"2026-07-05T04:06:08.787595+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZRIUZIRUSV4M","created_at":"2026-07-05T04:06:08.787595+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZRIUZIRUSV4MEFSG","created_at":"2026-07-05T04:06:08.787595+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZRIUZIRU","created_at":"2026-07-05T04:06:08.787595+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":20,"is_internal_anchor":false},{"citing_arxiv_id":"2603.18779","citing_title":"SoK: Practical Aspects of Releasing Differentially Private Graphs","ref_index":112,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZRIUZIRUSV4MEFSGVG6YM3TOBY","json":"https://pith.science/pith/ZRIUZIRUSV4MEFSGVG6YM3TOBY.json","graph_json":"https://pith.science/api/pith-number/ZRIUZIRUSV4MEFSGVG6YM3TOBY/graph.json","events_json":"https://pith.science/api/pith-number/ZRIUZIRUSV4MEFSGVG6YM3TOBY/events.json","paper":"https://pith.science/paper/ZRIUZIRU"},"agent_actions":{"view_html":"https://pith.science/pith/ZRIUZIRUSV4MEFSGVG6YM3TOBY","download_json":"https://pith.science/pith/ZRIUZIRUSV4MEFSGVG6YM3TOBY.json","view_paper":"https://pith.science/paper/ZRIUZIRU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.09205&json=true","fetch_graph":"https://pith.science/api/pith-number/ZRIUZIRUSV4MEFSGVG6YM3TOBY/graph.json","fetch_events":"https://pith.science/api/pith-number/ZRIUZIRUSV4MEFSGVG6YM3TOBY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZRIUZIRUSV4MEFSGVG6YM3TOBY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZRIUZIRUSV4MEFSGVG6YM3TOBY/action/storage_attestation","attest_author":"https://pith.science/pith/ZRIUZIRUSV4MEFSGVG6YM3TOBY/action/author_attestation","sign_citation":"https://pith.science/pith/ZRIUZIRUSV4MEFSGVG6YM3TOBY/action/citation_signature","submit_replication":"https://pith.science/pith/ZRIUZIRUSV4MEFSGVG6YM3TOBY/action/replication_record"}},"created_at":"2026-07-05T04:06:08.787595+00:00","updated_at":"2026-07-05T04:06:08.787595+00:00"}