{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:OROOG2WREPUWO2VXGHIUXTBRAW","short_pith_number":"pith:OROOG2WR","schema_version":"1.0","canonical_sha256":"745ce36ad123e9676ab731d14bcc3105a4dc2928239bc60a3d6dd50df08ad7df","source":{"kind":"arxiv","id":"2006.13039","version":5},"attestation_state":"computed","paper":{"title":"D2P-Fed: Differentially Private Federated Learning With Efficient Communication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Dawn Song, Lun Wang, Ruoxi Jia","submitted_at":"2020-06-22T06:46:11Z","abstract_excerpt":"In this paper, we propose the discrete Gaussian based differentially private federated learning (D2P-Fed), a unified scheme to achieve both differential privacy (DP) and communication efficiency in federated learning (FL). In particular, compared with the only prior work taking care of both aspects, D2P-Fed provides stronger privacy guarantee, better composability and smaller communication cost. The key idea is to apply the discrete Gaussian noise to the private data transmission. We provide complete analysis of the privacy guarantee, communication cost and convergence rate of D2P-Fed. We eval"},"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":"2006.13039","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-06-22T06:46:11Z","cross_cats_sorted":["cs.CR","cs.LG","stat.ME"],"title_canon_sha256":"1af22525cb8834c21d852cc7d73bf64497b1dc25cf6980271e1eac99d6047095","abstract_canon_sha256":"a3c3f54fbffbbb588b05ee74bdf1e419193896af8998cd8660dd09dd85c8f8d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:04:08.624054Z","signature_b64":"SCnVBLDovDWy//rnBxEeuPnoswA2dw2DZvPJ7ZhJp6X8JxFj1J7Roz9vmx1Y/aMlmWbIGAuS57EYBX+bma6NAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"745ce36ad123e9676ab731d14bcc3105a4dc2928239bc60a3d6dd50df08ad7df","last_reissued_at":"2026-07-05T02:04:08.623582Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:04:08.623582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"D2P-Fed: Differentially Private Federated Learning With Efficient Communication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Dawn Song, Lun Wang, Ruoxi Jia","submitted_at":"2020-06-22T06:46:11Z","abstract_excerpt":"In this paper, we propose the discrete Gaussian based differentially private federated learning (D2P-Fed), a unified scheme to achieve both differential privacy (DP) and communication efficiency in federated learning (FL). In particular, compared with the only prior work taking care of both aspects, D2P-Fed provides stronger privacy guarantee, better composability and smaller communication cost. The key idea is to apply the discrete Gaussian noise to the private data transmission. We provide complete analysis of the privacy guarantee, communication cost and convergence rate of D2P-Fed. We eval"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13039","kind":"arxiv","version":5},"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/2006.13039/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":"2006.13039","created_at":"2026-07-05T02:04:08.623643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.13039v5","created_at":"2026-07-05T02:04:08.623643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13039","created_at":"2026-07-05T02:04:08.623643+00:00"},{"alias_kind":"pith_short_12","alias_value":"OROOG2WREPUW","created_at":"2026-07-05T02:04:08.623643+00:00"},{"alias_kind":"pith_short_16","alias_value":"OROOG2WREPUWO2VX","created_at":"2026-07-05T02:04:08.623643+00:00"},{"alias_kind":"pith_short_8","alias_value":"OROOG2WR","created_at":"2026-07-05T02:04:08.623643+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07125","citing_title":"Scalable and Private Federated Learning Using Distributed Differential Privacy and Secure Aggregation","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OROOG2WREPUWO2VXGHIUXTBRAW","json":"https://pith.science/pith/OROOG2WREPUWO2VXGHIUXTBRAW.json","graph_json":"https://pith.science/api/pith-number/OROOG2WREPUWO2VXGHIUXTBRAW/graph.json","events_json":"https://pith.science/api/pith-number/OROOG2WREPUWO2VXGHIUXTBRAW/events.json","paper":"https://pith.science/paper/OROOG2WR"},"agent_actions":{"view_html":"https://pith.science/pith/OROOG2WREPUWO2VXGHIUXTBRAW","download_json":"https://pith.science/pith/OROOG2WREPUWO2VXGHIUXTBRAW.json","view_paper":"https://pith.science/paper/OROOG2WR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.13039&json=true","fetch_graph":"https://pith.science/api/pith-number/OROOG2WREPUWO2VXGHIUXTBRAW/graph.json","fetch_events":"https://pith.science/api/pith-number/OROOG2WREPUWO2VXGHIUXTBRAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OROOG2WREPUWO2VXGHIUXTBRAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OROOG2WREPUWO2VXGHIUXTBRAW/action/storage_attestation","attest_author":"https://pith.science/pith/OROOG2WREPUWO2VXGHIUXTBRAW/action/author_attestation","sign_citation":"https://pith.science/pith/OROOG2WREPUWO2VXGHIUXTBRAW/action/citation_signature","submit_replication":"https://pith.science/pith/OROOG2WREPUWO2VXGHIUXTBRAW/action/replication_record"}},"created_at":"2026-07-05T02:04:08.623643+00:00","updated_at":"2026-07-05T02:04:08.623643+00:00"}