{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EEDQZU25O424GDIVP7XO7JHMMA","short_pith_number":"pith:EEDQZU25","schema_version":"1.0","canonical_sha256":"21070cd35d7735c30d157feeefa4ec603e6802b921158816fc3f5f57e04592d7","source":{"kind":"arxiv","id":"2412.18513","version":1},"attestation_state":"computed","paper":{"title":"FedGIG: Graph Inversion from Gradient in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Haozhao Wang, Ruixuan Li, Tianzhe Xiao, Yichen Li, Yining Qi","submitted_at":"2024-12-24T15:52:21Z","abstract_excerpt":"Recent studies have shown that Federated learning (FL) is vulnerable to Gradient Inversion Attacks (GIA), which can recover private training data from shared gradients. However, existing methods are designed for dense, continuous data such as images or vectorized texts, and cannot be directly applied to sparse and discrete graph data. This paper first explores GIA's impact on Federated Graph Learning (FGL) and introduces Graph Inversion from Gradient in Federated Learning (FedGIG), a novel GIA method specifically designed for graph-structured data. FedGIG includes the adjacency matrix constrai"},"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":"2412.18513","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-24T15:52:21Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"6934b8b057ba8e6f288fea7207e803532bb89624b81d95d5bb8bd8635c921fb2","abstract_canon_sha256":"f4cbd1c9b3e45086c7fa78fcc836472668938cb5d03325e86db54669c6d8e24d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:56.871283Z","signature_b64":"ret+N+pgyXiAvVeYPrXoVPu4iWCwRPVdEsqM7h0n9PYOnuyr2JLRuw63+5vXLWii/Jaf5soptFmWx3dKXI6yCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21070cd35d7735c30d157feeefa4ec603e6802b921158816fc3f5f57e04592d7","last_reissued_at":"2026-07-05T09:53:56.870885Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:56.870885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedGIG: Graph Inversion from Gradient in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Haozhao Wang, Ruixuan Li, Tianzhe Xiao, Yichen Li, Yining Qi","submitted_at":"2024-12-24T15:52:21Z","abstract_excerpt":"Recent studies have shown that Federated learning (FL) is vulnerable to Gradient Inversion Attacks (GIA), which can recover private training data from shared gradients. However, existing methods are designed for dense, continuous data such as images or vectorized texts, and cannot be directly applied to sparse and discrete graph data. This paper first explores GIA's impact on Federated Graph Learning (FGL) and introduces Graph Inversion from Gradient in Federated Learning (FedGIG), a novel GIA method specifically designed for graph-structured data. FedGIG includes the adjacency matrix constrai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18513","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/2412.18513/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":"2412.18513","created_at":"2026-07-05T09:53:56.870942+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18513v1","created_at":"2026-07-05T09:53:56.870942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18513","created_at":"2026-07-05T09:53:56.870942+00:00"},{"alias_kind":"pith_short_12","alias_value":"EEDQZU25O424","created_at":"2026-07-05T09:53:56.870942+00:00"},{"alias_kind":"pith_short_16","alias_value":"EEDQZU25O424GDIV","created_at":"2026-07-05T09:53:56.870942+00:00"},{"alias_kind":"pith_short_8","alias_value":"EEDQZU25","created_at":"2026-07-05T09:53:56.870942+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.19641","citing_title":"Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses","ref_index":137,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EEDQZU25O424GDIVP7XO7JHMMA","json":"https://pith.science/pith/EEDQZU25O424GDIVP7XO7JHMMA.json","graph_json":"https://pith.science/api/pith-number/EEDQZU25O424GDIVP7XO7JHMMA/graph.json","events_json":"https://pith.science/api/pith-number/EEDQZU25O424GDIVP7XO7JHMMA/events.json","paper":"https://pith.science/paper/EEDQZU25"},"agent_actions":{"view_html":"https://pith.science/pith/EEDQZU25O424GDIVP7XO7JHMMA","download_json":"https://pith.science/pith/EEDQZU25O424GDIVP7XO7JHMMA.json","view_paper":"https://pith.science/paper/EEDQZU25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18513&json=true","fetch_graph":"https://pith.science/api/pith-number/EEDQZU25O424GDIVP7XO7JHMMA/graph.json","fetch_events":"https://pith.science/api/pith-number/EEDQZU25O424GDIVP7XO7JHMMA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EEDQZU25O424GDIVP7XO7JHMMA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EEDQZU25O424GDIVP7XO7JHMMA/action/storage_attestation","attest_author":"https://pith.science/pith/EEDQZU25O424GDIVP7XO7JHMMA/action/author_attestation","sign_citation":"https://pith.science/pith/EEDQZU25O424GDIVP7XO7JHMMA/action/citation_signature","submit_replication":"https://pith.science/pith/EEDQZU25O424GDIVP7XO7JHMMA/action/replication_record"}},"created_at":"2026-07-05T09:53:56.870942+00:00","updated_at":"2026-07-05T09:53:56.870942+00:00"}