{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KRUYE2XCAEJTOHGHQROOBX3QIV","short_pith_number":"pith:KRUYE2XC","schema_version":"1.0","canonical_sha256":"5469826ae20113371cc7845ce0df7045766e61253fa159f6b6673d7afbb49334","source":{"kind":"arxiv","id":"2606.04069","version":1},"attestation_state":"computed","paper":{"title":"Bayesian Membership Privacy for Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Megha Khosla, Sinan Y{\\i}ld{\\i}r{\\i}m","submitted_at":"2026-06-02T14:33:24Z","abstract_excerpt":"Existing privacy analyses for Graph Neural Networks (GNNs) largely inherit assumptions from non-graph settings, overlooking structural correlations and stochastic training-graph sampling. In particular, node-dependent priors make type-I and type-II errors alone insufficient to characterize the best membership inference test. To address this, we introduce Bayesian Membership Privacy (BMP), a sampling-aware formulation of node-level membership privacy that incorporates node-dependent priors and treats graph sampling probabilities as part of the adversary's knowledge. BMP casts membership inferen"},"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":"2606.04069","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-02T14:33:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"53f7e9992447ccc7419c5cbaf7bd095a8935f9acec3706552b60520bd2251832","abstract_canon_sha256":"9cc4c2d453049ffd85fc5eafca0513ba3213a8d8a92a5a0a80059f862544c642"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T00:06:45.675927Z","signature_b64":"hl9YCkWcjdAgHzW5/25vfmE6I9Gus70hf31sPzos9rVC6GKSF7uIZ1IKXgL1VPJ/4GD56x64JTE88BihkqwUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5469826ae20113371cc7845ce0df7045766e61253fa159f6b6673d7afbb49334","last_reissued_at":"2026-06-04T00:06:45.675543Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T00:06:45.675543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Membership Privacy for Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Megha Khosla, Sinan Y{\\i}ld{\\i}r{\\i}m","submitted_at":"2026-06-02T14:33:24Z","abstract_excerpt":"Existing privacy analyses for Graph Neural Networks (GNNs) largely inherit assumptions from non-graph settings, overlooking structural correlations and stochastic training-graph sampling. In particular, node-dependent priors make type-I and type-II errors alone insufficient to characterize the best membership inference test. To address this, we introduce Bayesian Membership Privacy (BMP), a sampling-aware formulation of node-level membership privacy that incorporates node-dependent priors and treats graph sampling probabilities as part of the adversary's knowledge. BMP casts membership inferen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04069","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/2606.04069/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":"2606.04069","created_at":"2026-06-04T00:06:45.675612+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04069v1","created_at":"2026-06-04T00:06:45.675612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04069","created_at":"2026-06-04T00:06:45.675612+00:00"},{"alias_kind":"pith_short_12","alias_value":"KRUYE2XCAEJT","created_at":"2026-06-04T00:06:45.675612+00:00"},{"alias_kind":"pith_short_16","alias_value":"KRUYE2XCAEJTOHGH","created_at":"2026-06-04T00:06:45.675612+00:00"},{"alias_kind":"pith_short_8","alias_value":"KRUYE2XC","created_at":"2026-06-04T00:06:45.675612+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/KRUYE2XCAEJTOHGHQROOBX3QIV","json":"https://pith.science/pith/KRUYE2XCAEJTOHGHQROOBX3QIV.json","graph_json":"https://pith.science/api/pith-number/KRUYE2XCAEJTOHGHQROOBX3QIV/graph.json","events_json":"https://pith.science/api/pith-number/KRUYE2XCAEJTOHGHQROOBX3QIV/events.json","paper":"https://pith.science/paper/KRUYE2XC"},"agent_actions":{"view_html":"https://pith.science/pith/KRUYE2XCAEJTOHGHQROOBX3QIV","download_json":"https://pith.science/pith/KRUYE2XCAEJTOHGHQROOBX3QIV.json","view_paper":"https://pith.science/paper/KRUYE2XC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04069&json=true","fetch_graph":"https://pith.science/api/pith-number/KRUYE2XCAEJTOHGHQROOBX3QIV/graph.json","fetch_events":"https://pith.science/api/pith-number/KRUYE2XCAEJTOHGHQROOBX3QIV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KRUYE2XCAEJTOHGHQROOBX3QIV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KRUYE2XCAEJTOHGHQROOBX3QIV/action/storage_attestation","attest_author":"https://pith.science/pith/KRUYE2XCAEJTOHGHQROOBX3QIV/action/author_attestation","sign_citation":"https://pith.science/pith/KRUYE2XCAEJTOHGHQROOBX3QIV/action/citation_signature","submit_replication":"https://pith.science/pith/KRUYE2XCAEJTOHGHQROOBX3QIV/action/replication_record"}},"created_at":"2026-06-04T00:06:45.675612+00:00","updated_at":"2026-06-04T00:06:45.675612+00:00"}