{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UR5L76YKAKI7MXMTCQNI4RX25J","short_pith_number":"pith:UR5L76YK","schema_version":"1.0","canonical_sha256":"a47abffb0a0291f65d93141a8e46faea5a5f409332296b9de1fa46a000e6d9b2","source":{"kind":"arxiv","id":"1911.00222","version":2},"attestation_state":"computed","paper":{"title":"Federated Learning with Differential Privacy: Algorithms and Performance Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NI"],"primary_cat":"cs.LG","authors_text":"Chuan Ma, Farokhi Farhad, Howard H. Yang, H. Vincent Poor, Jun Li, Kang Wei, Ming Ding, Shi Jin, Tony Q. S. Quek","submitted_at":"2019-11-01T06:36:33Z","abstract_excerpt":"In this paper, to effectively prevent information leakage, we propose a novel framework based on the concept of differential privacy (DP), in which artificial noises are added to the parameters at the clients side before aggregating, namely, noising before model aggregation FL (NbAFL). First, we prove that the NbAFL can satisfy DP under distinct protection levels by properly adapting different variances of artificial noises. Then we develop a theoretical convergence bound of the loss function of the trained FL model in the NbAFL. Specifically, the theoretical bound reveals the following three "},"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":"1911.00222","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-01T06:36:33Z","cross_cats_sorted":["cs.NI"],"title_canon_sha256":"de6baf9cdfc00f4e23855bb4cbeafe0e381153ab2a2110f69fbd3fde00a683f7","abstract_canon_sha256":"9a316c236c10ee9669a617a5ff471ce00aa619c2b89f52d74074f44d09aa6fe6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:17:55.902361Z","signature_b64":"c+YaN6/imXeiStVGoXXkMhTZH8Z2WLtGrKqhbQ3MAk6f7inbkpKGG8oo9Oc9VLQR1W3SvhgEsPXi+fCiiARJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a47abffb0a0291f65d93141a8e46faea5a5f409332296b9de1fa46a000e6d9b2","last_reissued_at":"2026-07-05T00:17:55.901893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:17:55.901893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Learning with Differential Privacy: Algorithms and Performance Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NI"],"primary_cat":"cs.LG","authors_text":"Chuan Ma, Farokhi Farhad, Howard H. Yang, H. Vincent Poor, Jun Li, Kang Wei, Ming Ding, Shi Jin, Tony Q. S. Quek","submitted_at":"2019-11-01T06:36:33Z","abstract_excerpt":"In this paper, to effectively prevent information leakage, we propose a novel framework based on the concept of differential privacy (DP), in which artificial noises are added to the parameters at the clients side before aggregating, namely, noising before model aggregation FL (NbAFL). First, we prove that the NbAFL can satisfy DP under distinct protection levels by properly adapting different variances of artificial noises. Then we develop a theoretical convergence bound of the loss function of the trained FL model in the NbAFL. Specifically, the theoretical bound reveals the following three "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.00222","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/1911.00222/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":"1911.00222","created_at":"2026-07-05T00:17:55.901957+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.00222v2","created_at":"2026-07-05T00:17:55.901957+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.00222","created_at":"2026-07-05T00:17:55.901957+00:00"},{"alias_kind":"pith_short_12","alias_value":"UR5L76YKAKI7","created_at":"2026-07-05T00:17:55.901957+00:00"},{"alias_kind":"pith_short_16","alias_value":"UR5L76YKAKI7MXMT","created_at":"2026-07-05T00:17:55.901957+00:00"},{"alias_kind":"pith_short_8","alias_value":"UR5L76YK","created_at":"2026-07-05T00:17:55.901957+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20518","citing_title":"WallStreetFeds: Client-Specific Tokens as Investment Vehicles in Federated Learning","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UR5L76YKAKI7MXMTCQNI4RX25J","json":"https://pith.science/pith/UR5L76YKAKI7MXMTCQNI4RX25J.json","graph_json":"https://pith.science/api/pith-number/UR5L76YKAKI7MXMTCQNI4RX25J/graph.json","events_json":"https://pith.science/api/pith-number/UR5L76YKAKI7MXMTCQNI4RX25J/events.json","paper":"https://pith.science/paper/UR5L76YK"},"agent_actions":{"view_html":"https://pith.science/pith/UR5L76YKAKI7MXMTCQNI4RX25J","download_json":"https://pith.science/pith/UR5L76YKAKI7MXMTCQNI4RX25J.json","view_paper":"https://pith.science/paper/UR5L76YK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.00222&json=true","fetch_graph":"https://pith.science/api/pith-number/UR5L76YKAKI7MXMTCQNI4RX25J/graph.json","fetch_events":"https://pith.science/api/pith-number/UR5L76YKAKI7MXMTCQNI4RX25J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UR5L76YKAKI7MXMTCQNI4RX25J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UR5L76YKAKI7MXMTCQNI4RX25J/action/storage_attestation","attest_author":"https://pith.science/pith/UR5L76YKAKI7MXMTCQNI4RX25J/action/author_attestation","sign_citation":"https://pith.science/pith/UR5L76YKAKI7MXMTCQNI4RX25J/action/citation_signature","submit_replication":"https://pith.science/pith/UR5L76YKAKI7MXMTCQNI4RX25J/action/replication_record"}},"created_at":"2026-07-05T00:17:55.901957+00:00","updated_at":"2026-07-05T00:17:55.901957+00:00"}