{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:THGSRAJ3MQKKIOR3TBCPSHEYAC","short_pith_number":"pith:THGSRAJ3","schema_version":"1.0","canonical_sha256":"99cd28813b6414a43a3b9844f91c9800bab1147989addda1d1cf5f2c49f31bae","source":{"kind":"arxiv","id":"2109.13012","version":1},"attestation_state":"computed","paper":{"title":"Federated Deep Learning with Bayesian Privacy","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Bowen Li, Hanlin Gu, Lixin Fan, Qiang Yang, Yan Kang, Yuan Yao","submitted_at":"2021-09-27T12:48:40Z","abstract_excerpt":"Federated learning (FL) aims to protect data privacy by cooperatively learning a model without sharing private data among users. For Federated Learning of Deep Neural Network with billions of model parameters, existing privacy-preserving solutions are unsatisfactory. Homomorphic encryption (HE) based methods provide secure privacy protections but suffer from extremely high computational and communication overheads rendering it almost useless in practice . Deep learning with Differential Privacy (DP) was implemented as a practical learning algorithm at a manageable cost in complexity. However, "},"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":"2109.13012","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-27T12:48:40Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"5694f99547e090f49a7cc7900c5ef9d073c7ceb6a89ad59a66eca479f2313665","abstract_canon_sha256":"d6c90dd3aeb5b617c13f673806b2a296872abd8411c9305ce177715d31134475"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:17:40.234820Z","signature_b64":"j+13IYfiSewj4Gm8KTYTjLP8c2rlO75sXS7aRVT0K5+86MKEZmqPoDtBSrZ5/Bfb3TUlZlCLM0VdKDgu7hfHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99cd28813b6414a43a3b9844f91c9800bab1147989addda1d1cf5f2c49f31bae","last_reissued_at":"2026-07-05T03:17:40.234340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:17:40.234340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Deep Learning with Bayesian Privacy","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Bowen Li, Hanlin Gu, Lixin Fan, Qiang Yang, Yan Kang, Yuan Yao","submitted_at":"2021-09-27T12:48:40Z","abstract_excerpt":"Federated learning (FL) aims to protect data privacy by cooperatively learning a model without sharing private data among users. For Federated Learning of Deep Neural Network with billions of model parameters, existing privacy-preserving solutions are unsatisfactory. Homomorphic encryption (HE) based methods provide secure privacy protections but suffer from extremely high computational and communication overheads rendering it almost useless in practice . Deep learning with Differential Privacy (DP) was implemented as a practical learning algorithm at a manageable cost in complexity. However, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.13012","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/2109.13012/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":"2109.13012","created_at":"2026-07-05T03:17:40.234399+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.13012v1","created_at":"2026-07-05T03:17:40.234399+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.13012","created_at":"2026-07-05T03:17:40.234399+00:00"},{"alias_kind":"pith_short_12","alias_value":"THGSRAJ3MQKK","created_at":"2026-07-05T03:17:40.234399+00:00"},{"alias_kind":"pith_short_16","alias_value":"THGSRAJ3MQKKIOR3","created_at":"2026-07-05T03:17:40.234399+00:00"},{"alias_kind":"pith_short_8","alias_value":"THGSRAJ3","created_at":"2026-07-05T03:17:40.234399+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19015","citing_title":"FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/THGSRAJ3MQKKIOR3TBCPSHEYAC","json":"https://pith.science/pith/THGSRAJ3MQKKIOR3TBCPSHEYAC.json","graph_json":"https://pith.science/api/pith-number/THGSRAJ3MQKKIOR3TBCPSHEYAC/graph.json","events_json":"https://pith.science/api/pith-number/THGSRAJ3MQKKIOR3TBCPSHEYAC/events.json","paper":"https://pith.science/paper/THGSRAJ3"},"agent_actions":{"view_html":"https://pith.science/pith/THGSRAJ3MQKKIOR3TBCPSHEYAC","download_json":"https://pith.science/pith/THGSRAJ3MQKKIOR3TBCPSHEYAC.json","view_paper":"https://pith.science/paper/THGSRAJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.13012&json=true","fetch_graph":"https://pith.science/api/pith-number/THGSRAJ3MQKKIOR3TBCPSHEYAC/graph.json","fetch_events":"https://pith.science/api/pith-number/THGSRAJ3MQKKIOR3TBCPSHEYAC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/THGSRAJ3MQKKIOR3TBCPSHEYAC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/THGSRAJ3MQKKIOR3TBCPSHEYAC/action/storage_attestation","attest_author":"https://pith.science/pith/THGSRAJ3MQKKIOR3TBCPSHEYAC/action/author_attestation","sign_citation":"https://pith.science/pith/THGSRAJ3MQKKIOR3TBCPSHEYAC/action/citation_signature","submit_replication":"https://pith.science/pith/THGSRAJ3MQKKIOR3TBCPSHEYAC/action/replication_record"}},"created_at":"2026-07-05T03:17:40.234399+00:00","updated_at":"2026-07-05T03:17:40.234399+00:00"}