{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3RIL7SFAX5JRF3HBGM5EESDJQU","short_pith_number":"pith:3RIL7SFA","schema_version":"1.0","canonical_sha256":"dc50bfc8a0bf5312ece1333a42486985028758b5207e3e2d9ecae48283338bc8","source":{"kind":"arxiv","id":"2008.07298","version":3},"attestation_state":"computed","paper":{"title":"WAFFLE: Watermarking in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","cs.LG","stat.ML"],"primary_cat":"cs.CR","authors_text":"Buse Gul Atli, N. Asokan, Samuel Marchal, Yuxi Xia","submitted_at":"2020-08-17T13:27:45Z","abstract_excerpt":"Federated learning is a distributed learning technique where machine learning models are trained on client devices in which the local training data resides. The training is coordinated via a central server which is, typically, controlled by the intended owner of the resulting model. By avoiding the need to transport the training data to the central server, federated learning improves privacy and efficiency. But it raises the risk of model theft by clients because the resulting model is available on every client device. Even if the application software used for local training may attempt to pre"},"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":"2008.07298","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2020-08-17T13:27:45Z","cross_cats_sorted":["cs.DC","cs.LG","stat.ML"],"title_canon_sha256":"e9d9f4ae1131237ab01cbbdcc4fa359b85bd5d1aea4ee74ef17f3e7a7809f294","abstract_canon_sha256":"4b6a5052de95e2103287757fb090f96ef9cb51bc20d990456990f63783f6f347"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:59:53.719494Z","signature_b64":"dvYEABp6y8dLKR83SkYCFbrl4Iiz8wcDEXzsXQsum+SB8j+KELkUNBVFjZD+c2K8a2FTQlKLHs7oxmdVzPf5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc50bfc8a0bf5312ece1333a42486985028758b5207e3e2d9ecae48283338bc8","last_reissued_at":"2026-07-05T02:59:53.719069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:59:53.719069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WAFFLE: Watermarking in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","cs.LG","stat.ML"],"primary_cat":"cs.CR","authors_text":"Buse Gul Atli, N. Asokan, Samuel Marchal, Yuxi Xia","submitted_at":"2020-08-17T13:27:45Z","abstract_excerpt":"Federated learning is a distributed learning technique where machine learning models are trained on client devices in which the local training data resides. The training is coordinated via a central server which is, typically, controlled by the intended owner of the resulting model. By avoiding the need to transport the training data to the central server, federated learning improves privacy and efficiency. But it raises the risk of model theft by clients because the resulting model is available on every client device. Even if the application software used for local training may attempt to pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.07298","kind":"arxiv","version":3},"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/2008.07298/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":"2008.07298","created_at":"2026-07-05T02:59:53.719128+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.07298v3","created_at":"2026-07-05T02:59:53.719128+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.07298","created_at":"2026-07-05T02:59:53.719128+00:00"},{"alias_kind":"pith_short_12","alias_value":"3RIL7SFAX5JR","created_at":"2026-07-05T02:59:53.719128+00:00"},{"alias_kind":"pith_short_16","alias_value":"3RIL7SFAX5JRF3HB","created_at":"2026-07-05T02:59:53.719128+00:00"},{"alias_kind":"pith_short_8","alias_value":"3RIL7SFA","created_at":"2026-07-05T02:59:53.719128+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/3RIL7SFAX5JRF3HBGM5EESDJQU","json":"https://pith.science/pith/3RIL7SFAX5JRF3HBGM5EESDJQU.json","graph_json":"https://pith.science/api/pith-number/3RIL7SFAX5JRF3HBGM5EESDJQU/graph.json","events_json":"https://pith.science/api/pith-number/3RIL7SFAX5JRF3HBGM5EESDJQU/events.json","paper":"https://pith.science/paper/3RIL7SFA"},"agent_actions":{"view_html":"https://pith.science/pith/3RIL7SFAX5JRF3HBGM5EESDJQU","download_json":"https://pith.science/pith/3RIL7SFAX5JRF3HBGM5EESDJQU.json","view_paper":"https://pith.science/paper/3RIL7SFA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.07298&json=true","fetch_graph":"https://pith.science/api/pith-number/3RIL7SFAX5JRF3HBGM5EESDJQU/graph.json","fetch_events":"https://pith.science/api/pith-number/3RIL7SFAX5JRF3HBGM5EESDJQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3RIL7SFAX5JRF3HBGM5EESDJQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3RIL7SFAX5JRF3HBGM5EESDJQU/action/storage_attestation","attest_author":"https://pith.science/pith/3RIL7SFAX5JRF3HBGM5EESDJQU/action/author_attestation","sign_citation":"https://pith.science/pith/3RIL7SFAX5JRF3HBGM5EESDJQU/action/citation_signature","submit_replication":"https://pith.science/pith/3RIL7SFAX5JRF3HBGM5EESDJQU/action/replication_record"}},"created_at":"2026-07-05T02:59:53.719128+00:00","updated_at":"2026-07-05T02:59:53.719128+00:00"}