{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YL66W5B4RKQBLT2WDN5MGAJREH","short_pith_number":"pith:YL66W5B4","schema_version":"1.0","canonical_sha256":"c2fdeb743c8aa015cf561b7ac3013121e706c4dc97847b7aac0e3c431e59b747","source":{"kind":"arxiv","id":"2308.02465","version":2},"attestation_state":"computed","paper":{"title":"Label Inference Attacks against Node-level Vertical Federated GNNs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Antonino Nocera, Jing Xu, Marco Arazzi, Marina Krcek, Mauro Conti, Stefanos Koffas, Stjepan Picek","submitted_at":"2023-08-04T17:04:58Z","abstract_excerpt":"Federated learning enables collaborative training of machine learning models by keeping the raw data of the involved workers private. Three of its main objectives are to improve the models' privacy, security, and scalability. Vertical Federated Learning (VFL) offers an efficient cross-silo setting where a few parties collaboratively train a model without sharing the same features. In such a scenario, classification labels are commonly considered sensitive information held exclusively by one (active) party, while other (passive) parties use only their local information. Recent works have uncove"},"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":"2308.02465","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-04T17:04:58Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"ac796c6e36f3c459bd997c7510a18ff1643d26d3e9e3ffed4ed4236ca94251f7","abstract_canon_sha256":"9c51f0ab264b6ebfcf4a9a22100dbb5201897c55a71578f44e28793704354557"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:24.568544Z","signature_b64":"wjOYdy5J0E4vSN+4Fc7YFxK9qg848NR/vSb8Eq6XmqUEaFxl6bnrCoQM3C6ysnR6AiejbppgLEEWQIppOjRmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2fdeb743c8aa015cf561b7ac3013121e706c4dc97847b7aac0e3c431e59b747","last_reissued_at":"2026-07-05T08:09:24.568084Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:24.568084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Label Inference Attacks against Node-level Vertical Federated GNNs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Antonino Nocera, Jing Xu, Marco Arazzi, Marina Krcek, Mauro Conti, Stefanos Koffas, Stjepan Picek","submitted_at":"2023-08-04T17:04:58Z","abstract_excerpt":"Federated learning enables collaborative training of machine learning models by keeping the raw data of the involved workers private. Three of its main objectives are to improve the models' privacy, security, and scalability. Vertical Federated Learning (VFL) offers an efficient cross-silo setting where a few parties collaboratively train a model without sharing the same features. In such a scenario, classification labels are commonly considered sensitive information held exclusively by one (active) party, while other (passive) parties use only their local information. Recent works have uncove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.02465","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/2308.02465/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":"2308.02465","created_at":"2026-07-05T08:09:24.568145+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.02465v2","created_at":"2026-07-05T08:09:24.568145+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.02465","created_at":"2026-07-05T08:09:24.568145+00:00"},{"alias_kind":"pith_short_12","alias_value":"YL66W5B4RKQB","created_at":"2026-07-05T08:09:24.568145+00:00"},{"alias_kind":"pith_short_16","alias_value":"YL66W5B4RKQBLT2W","created_at":"2026-07-05T08:09:24.568145+00:00"},{"alias_kind":"pith_short_8","alias_value":"YL66W5B4","created_at":"2026-07-05T08:09:24.568145+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.00407","citing_title":"Fed-Listing: Federated Label Distribution Inference in Graph Neural Networks","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YL66W5B4RKQBLT2WDN5MGAJREH","json":"https://pith.science/pith/YL66W5B4RKQBLT2WDN5MGAJREH.json","graph_json":"https://pith.science/api/pith-number/YL66W5B4RKQBLT2WDN5MGAJREH/graph.json","events_json":"https://pith.science/api/pith-number/YL66W5B4RKQBLT2WDN5MGAJREH/events.json","paper":"https://pith.science/paper/YL66W5B4"},"agent_actions":{"view_html":"https://pith.science/pith/YL66W5B4RKQBLT2WDN5MGAJREH","download_json":"https://pith.science/pith/YL66W5B4RKQBLT2WDN5MGAJREH.json","view_paper":"https://pith.science/paper/YL66W5B4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.02465&json=true","fetch_graph":"https://pith.science/api/pith-number/YL66W5B4RKQBLT2WDN5MGAJREH/graph.json","fetch_events":"https://pith.science/api/pith-number/YL66W5B4RKQBLT2WDN5MGAJREH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YL66W5B4RKQBLT2WDN5MGAJREH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YL66W5B4RKQBLT2WDN5MGAJREH/action/storage_attestation","attest_author":"https://pith.science/pith/YL66W5B4RKQBLT2WDN5MGAJREH/action/author_attestation","sign_citation":"https://pith.science/pith/YL66W5B4RKQBLT2WDN5MGAJREH/action/citation_signature","submit_replication":"https://pith.science/pith/YL66W5B4RKQBLT2WDN5MGAJREH/action/replication_record"}},"created_at":"2026-07-05T08:09:24.568145+00:00","updated_at":"2026-07-05T08:09:24.568145+00:00"}