{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AITKSH3HOYT4RJLQQBX2PYKGHY","short_pith_number":"pith:AITKSH3H","schema_version":"1.0","canonical_sha256":"0226a91f677627c8a570806fa7e1463e230f8f4301eadb9c31df4d316cc8a858","source":{"kind":"arxiv","id":"2102.11158","version":1},"attestation_state":"computed","paper":{"title":"Federated $f$-Differential Privacy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Qi Long, Qinqing Zheng, Shuxiao Chen, Weijie J. Su","submitted_at":"2021-02-22T16:28:21Z","abstract_excerpt":"Federated learning (FL) is a training paradigm where the clients collaboratively learn models by repeatedly sharing information without compromising much on the privacy of their local sensitive data. In this paper, we introduce federated $f$-differential privacy, a new notion specifically tailored to the federated setting, based on the framework of Gaussian differential privacy. Federated $f$-differential privacy operates on record level: it provides the privacy guarantee on each individual record of one client's data against adversaries. We then propose a generic private federated learning fr"},"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":"2102.11158","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-02-22T16:28:21Z","cross_cats_sorted":["cs.AI","cs.CR","cs.CV","cs.LG"],"title_canon_sha256":"890444ac16d0e2dfed87c02925f84fc632b7f7952d11c90d3fabe2972d54f4df","abstract_canon_sha256":"1813b121d36c5c12a4e1a5427ea52d3c641f31e0b441c57f2810466005076e63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:17:51.396722Z","signature_b64":"JVvsV27vkyaTnxSlEu2cAuioTzuvdTtz7LetZ9GiXLBhAz2cpGNVTxiWO2HcmBfwNH44pxnDG0PDbQLsq6uvCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0226a91f677627c8a570806fa7e1463e230f8f4301eadb9c31df4d316cc8a858","last_reissued_at":"2026-07-05T02:17:51.396299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:17:51.396299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated $f$-Differential Privacy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Qi Long, Qinqing Zheng, Shuxiao Chen, Weijie J. Su","submitted_at":"2021-02-22T16:28:21Z","abstract_excerpt":"Federated learning (FL) is a training paradigm where the clients collaboratively learn models by repeatedly sharing information without compromising much on the privacy of their local sensitive data. In this paper, we introduce federated $f$-differential privacy, a new notion specifically tailored to the federated setting, based on the framework of Gaussian differential privacy. Federated $f$-differential privacy operates on record level: it provides the privacy guarantee on each individual record of one client's data against adversaries. We then propose a generic private federated learning fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.11158","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/2102.11158/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":"2102.11158","created_at":"2026-07-05T02:17:51.396374+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.11158v1","created_at":"2026-07-05T02:17:51.396374+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.11158","created_at":"2026-07-05T02:17:51.396374+00:00"},{"alias_kind":"pith_short_12","alias_value":"AITKSH3HOYT4","created_at":"2026-07-05T02:17:51.396374+00:00"},{"alias_kind":"pith_short_16","alias_value":"AITKSH3HOYT4RJLQ","created_at":"2026-07-05T02:17:51.396374+00:00"},{"alias_kind":"pith_short_8","alias_value":"AITKSH3H","created_at":"2026-07-05T02:17:51.396374+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/AITKSH3HOYT4RJLQQBX2PYKGHY","json":"https://pith.science/pith/AITKSH3HOYT4RJLQQBX2PYKGHY.json","graph_json":"https://pith.science/api/pith-number/AITKSH3HOYT4RJLQQBX2PYKGHY/graph.json","events_json":"https://pith.science/api/pith-number/AITKSH3HOYT4RJLQQBX2PYKGHY/events.json","paper":"https://pith.science/paper/AITKSH3H"},"agent_actions":{"view_html":"https://pith.science/pith/AITKSH3HOYT4RJLQQBX2PYKGHY","download_json":"https://pith.science/pith/AITKSH3HOYT4RJLQQBX2PYKGHY.json","view_paper":"https://pith.science/paper/AITKSH3H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.11158&json=true","fetch_graph":"https://pith.science/api/pith-number/AITKSH3HOYT4RJLQQBX2PYKGHY/graph.json","fetch_events":"https://pith.science/api/pith-number/AITKSH3HOYT4RJLQQBX2PYKGHY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AITKSH3HOYT4RJLQQBX2PYKGHY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AITKSH3HOYT4RJLQQBX2PYKGHY/action/storage_attestation","attest_author":"https://pith.science/pith/AITKSH3HOYT4RJLQQBX2PYKGHY/action/author_attestation","sign_citation":"https://pith.science/pith/AITKSH3HOYT4RJLQQBX2PYKGHY/action/citation_signature","submit_replication":"https://pith.science/pith/AITKSH3HOYT4RJLQQBX2PYKGHY/action/replication_record"}},"created_at":"2026-07-05T02:17:51.396374+00:00","updated_at":"2026-07-05T02:17:51.396374+00:00"}