{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C7VHLSWEIKJ62FD2VEYYGJXD5R","short_pith_number":"pith:C7VHLSWE","schema_version":"1.0","canonical_sha256":"17ea75cac44293ed147aa9318326e3ec558e9ec9a8bfd8f1d25f30b98069b595","source":{"kind":"arxiv","id":"2606.29748","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Generative Reconstruction Attacks against Graph Neural Network Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Adebayo Keji, Sayanton Dibbo","submitted_at":"2026-06-29T03:44:51Z","abstract_excerpt":"The application of graph data in numerous disciplines raises the need for gathering and analyzing huge volumes of data, some of which is private and sensitive. The non-Euclidean nature of the graph data makes the analysis computationally challenging, leading to the use of Graph Neural Networks (GNNs) in the age of AI. GNNs may inadvertently leak sensitive data they are trained on, which raises serious data security issues, including the model inversion attack. In this study, we analyze GNNs' vulnerabilities by introducing two novel graph inversion (i.e., reconstruction) attacks: graph-label co"},"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":"2606.29748","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T03:44:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c278c4741bf7ff9581d2dbb25b7ef2cd6b6897cd0a4b3a2d3be4a24c1b3c5ff1","abstract_canon_sha256":"3ea58d8c6e3c9001c009107efc82815744dc51445dcae954db3a8b9dbc3ea55a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:33.362924Z","signature_b64":"6x/XPuLlEopbN7hu2fIZpvb61VyaLSn5LIboTlc8JZCX/jKG1SuINroR4hXXYVf2NnE+95lZ6TI9xtiOp82MBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17ea75cac44293ed147aa9318326e3ec558e9ec9a8bfd8f1d25f30b98069b595","last_reissued_at":"2026-06-30T02:17:33.362281Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:33.362281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Generative Reconstruction Attacks against Graph Neural Network Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Adebayo Keji, Sayanton Dibbo","submitted_at":"2026-06-29T03:44:51Z","abstract_excerpt":"The application of graph data in numerous disciplines raises the need for gathering and analyzing huge volumes of data, some of which is private and sensitive. The non-Euclidean nature of the graph data makes the analysis computationally challenging, leading to the use of Graph Neural Networks (GNNs) in the age of AI. GNNs may inadvertently leak sensitive data they are trained on, which raises serious data security issues, including the model inversion attack. In this study, we analyze GNNs' vulnerabilities by introducing two novel graph inversion (i.e., reconstruction) attacks: graph-label co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29748","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/2606.29748/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":"2606.29748","created_at":"2026-06-30T02:17:33.362399+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29748v1","created_at":"2026-06-30T02:17:33.362399+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29748","created_at":"2026-06-30T02:17:33.362399+00:00"},{"alias_kind":"pith_short_12","alias_value":"C7VHLSWEIKJ6","created_at":"2026-06-30T02:17:33.362399+00:00"},{"alias_kind":"pith_short_16","alias_value":"C7VHLSWEIKJ62FD2","created_at":"2026-06-30T02:17:33.362399+00:00"},{"alias_kind":"pith_short_8","alias_value":"C7VHLSWE","created_at":"2026-06-30T02:17:33.362399+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/C7VHLSWEIKJ62FD2VEYYGJXD5R","json":"https://pith.science/pith/C7VHLSWEIKJ62FD2VEYYGJXD5R.json","graph_json":"https://pith.science/api/pith-number/C7VHLSWEIKJ62FD2VEYYGJXD5R/graph.json","events_json":"https://pith.science/api/pith-number/C7VHLSWEIKJ62FD2VEYYGJXD5R/events.json","paper":"https://pith.science/paper/C7VHLSWE"},"agent_actions":{"view_html":"https://pith.science/pith/C7VHLSWEIKJ62FD2VEYYGJXD5R","download_json":"https://pith.science/pith/C7VHLSWEIKJ62FD2VEYYGJXD5R.json","view_paper":"https://pith.science/paper/C7VHLSWE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29748&json=true","fetch_graph":"https://pith.science/api/pith-number/C7VHLSWEIKJ62FD2VEYYGJXD5R/graph.json","fetch_events":"https://pith.science/api/pith-number/C7VHLSWEIKJ62FD2VEYYGJXD5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C7VHLSWEIKJ62FD2VEYYGJXD5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C7VHLSWEIKJ62FD2VEYYGJXD5R/action/storage_attestation","attest_author":"https://pith.science/pith/C7VHLSWEIKJ62FD2VEYYGJXD5R/action/author_attestation","sign_citation":"https://pith.science/pith/C7VHLSWEIKJ62FD2VEYYGJXD5R/action/citation_signature","submit_replication":"https://pith.science/pith/C7VHLSWEIKJ62FD2VEYYGJXD5R/action/replication_record"}},"created_at":"2026-06-30T02:17:33.362399+00:00","updated_at":"2026-06-30T02:17:33.362399+00:00"}