{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O2SWFWEZMWFN6VYIG57DTOKFVY","short_pith_number":"pith:O2SWFWEZ","schema_version":"1.0","canonical_sha256":"76a562d899658adf5708377e39b945ae1458976be5ad5e38625ebe381eb6b850","source":{"kind":"arxiv","id":"2405.05784","version":1},"attestation_state":"computed","paper":{"title":"Link Stealing Attacks Against Inductive Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Mathias Humbert, Michael Backes, Neil Zhenqiang Gong, Pascal Berrang, Xinlei He, Yang Zhang, Yixin Wu","submitted_at":"2024-05-09T14:03:52Z","abstract_excerpt":"A graph neural network (GNN) is a type of neural network that is specifically designed to process graph-structured data. Typically, GNNs can be implemented in two settings, including the transductive setting and the inductive setting. In the transductive setting, the trained model can only predict the labels of nodes that were observed at the training time. In the inductive setting, the trained model can be generalized to new nodes/graphs. Due to its flexibility, the inductive setting is the most popular GNN setting at the moment. Previous work has shown that transductive GNNs are vulnerable t"},"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":"2405.05784","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-05-09T14:03:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"df3a63f590e1a0dc7b16e79389dad3f97f7d76efc4ef0bfe817655bf55d156ca","abstract_canon_sha256":"ea3b4637044d0fe351e6dcfeab03175f9c66b837d9c781e8060ee3f15c45771e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:22.709276Z","signature_b64":"BbUlYk5EW/XiyAwpN0/T/POr7ekm/g96UWd72qEhjIAa9gNVOCtbO8LEwI3iURfi5oXWUUQKVDbNIKGueSM9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76a562d899658adf5708377e39b945ae1458976be5ad5e38625ebe381eb6b850","last_reissued_at":"2026-07-05T08:17:22.708719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:22.708719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Link Stealing Attacks Against Inductive Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Mathias Humbert, Michael Backes, Neil Zhenqiang Gong, Pascal Berrang, Xinlei He, Yang Zhang, Yixin Wu","submitted_at":"2024-05-09T14:03:52Z","abstract_excerpt":"A graph neural network (GNN) is a type of neural network that is specifically designed to process graph-structured data. Typically, GNNs can be implemented in two settings, including the transductive setting and the inductive setting. In the transductive setting, the trained model can only predict the labels of nodes that were observed at the training time. In the inductive setting, the trained model can be generalized to new nodes/graphs. Due to its flexibility, the inductive setting is the most popular GNN setting at the moment. Previous work has shown that transductive GNNs are vulnerable t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.05784","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/2405.05784/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":"2405.05784","created_at":"2026-07-05T08:17:22.708779+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.05784v1","created_at":"2026-07-05T08:17:22.708779+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.05784","created_at":"2026-07-05T08:17:22.708779+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2SWFWEZMWFN","created_at":"2026-07-05T08:17:22.708779+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2SWFWEZMWFN6VYI","created_at":"2026-07-05T08:17:22.708779+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2SWFWEZ","created_at":"2026-07-05T08:17:22.708779+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.15031","citing_title":"A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives","ref_index":227,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O2SWFWEZMWFN6VYIG57DTOKFVY","json":"https://pith.science/pith/O2SWFWEZMWFN6VYIG57DTOKFVY.json","graph_json":"https://pith.science/api/pith-number/O2SWFWEZMWFN6VYIG57DTOKFVY/graph.json","events_json":"https://pith.science/api/pith-number/O2SWFWEZMWFN6VYIG57DTOKFVY/events.json","paper":"https://pith.science/paper/O2SWFWEZ"},"agent_actions":{"view_html":"https://pith.science/pith/O2SWFWEZMWFN6VYIG57DTOKFVY","download_json":"https://pith.science/pith/O2SWFWEZMWFN6VYIG57DTOKFVY.json","view_paper":"https://pith.science/paper/O2SWFWEZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.05784&json=true","fetch_graph":"https://pith.science/api/pith-number/O2SWFWEZMWFN6VYIG57DTOKFVY/graph.json","fetch_events":"https://pith.science/api/pith-number/O2SWFWEZMWFN6VYIG57DTOKFVY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2SWFWEZMWFN6VYIG57DTOKFVY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2SWFWEZMWFN6VYIG57DTOKFVY/action/storage_attestation","attest_author":"https://pith.science/pith/O2SWFWEZMWFN6VYIG57DTOKFVY/action/author_attestation","sign_citation":"https://pith.science/pith/O2SWFWEZMWFN6VYIG57DTOKFVY/action/citation_signature","submit_replication":"https://pith.science/pith/O2SWFWEZMWFN6VYIG57DTOKFVY/action/replication_record"}},"created_at":"2026-07-05T08:17:22.708779+00:00","updated_at":"2026-07-05T08:17:22.708779+00:00"}