{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UUMRN73ZDQJXHVBHWTKHVXRJBG","short_pith_number":"pith:UUMRN73Z","schema_version":"1.0","canonical_sha256":"a51916ff791c1373d427b4d47ade290981544e41c5c047399743bc56d4e6232d","source":{"kind":"arxiv","id":"2009.05537","version":2},"attestation_state":"computed","paper":{"title":"Federated Model Distillation with Noise-Free Differential Privacy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CR","authors_text":"Lichao Sun, Lingjuan Lyu","submitted_at":"2020-09-11T17:19:56Z","abstract_excerpt":"Conventional federated learning directly averages model weights, which is only possible for collaboration between models with homogeneous architectures. Sharing prediction instead of weight removes this obstacle and eliminates the risk of white-box inference attacks in conventional federated learning. However, the predictions from local models are sensitive and would leak training data privacy to the public. To address this issue, one naive approach is adding the differentially private random noise to the predictions, which however brings a substantial trade-off between privacy budget and mode"},"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":"2009.05537","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2020-09-11T17:19:56Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"1c6d79ec9d4d219c8d08e1740ff5d55949f950b95f5384befd383a47c06ccfff","abstract_canon_sha256":"701ef5ecbda583134041e7060cf2889f4c9e3d1f54f5d2e61311cbf5c4293d93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:02.175181Z","signature_b64":"NbU0XZeHCcGwmqzJhjw8/5jpWHCQ1cdzQHoie8PzW774V9FkDQHxsKSO99t0XFrWjmcl6mYZLZo7hpy7rQ+gCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a51916ff791c1373d427b4d47ade290981544e41c5c047399743bc56d4e6232d","last_reissued_at":"2026-07-05T02:42:02.174823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:02.174823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Model Distillation with Noise-Free Differential Privacy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CR","authors_text":"Lichao Sun, Lingjuan Lyu","submitted_at":"2020-09-11T17:19:56Z","abstract_excerpt":"Conventional federated learning directly averages model weights, which is only possible for collaboration between models with homogeneous architectures. Sharing prediction instead of weight removes this obstacle and eliminates the risk of white-box inference attacks in conventional federated learning. However, the predictions from local models are sensitive and would leak training data privacy to the public. To address this issue, one naive approach is adding the differentially private random noise to the predictions, which however brings a substantial trade-off between privacy budget and mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.05537","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/2009.05537/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":"2009.05537","created_at":"2026-07-05T02:42:02.174885+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.05537v2","created_at":"2026-07-05T02:42:02.174885+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.05537","created_at":"2026-07-05T02:42:02.174885+00:00"},{"alias_kind":"pith_short_12","alias_value":"UUMRN73ZDQJX","created_at":"2026-07-05T02:42:02.174885+00:00"},{"alias_kind":"pith_short_16","alias_value":"UUMRN73ZDQJXHVBH","created_at":"2026-07-05T02:42:02.174885+00:00"},{"alias_kind":"pith_short_8","alias_value":"UUMRN73Z","created_at":"2026-07-05T02:42:02.174885+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/UUMRN73ZDQJXHVBHWTKHVXRJBG","json":"https://pith.science/pith/UUMRN73ZDQJXHVBHWTKHVXRJBG.json","graph_json":"https://pith.science/api/pith-number/UUMRN73ZDQJXHVBHWTKHVXRJBG/graph.json","events_json":"https://pith.science/api/pith-number/UUMRN73ZDQJXHVBHWTKHVXRJBG/events.json","paper":"https://pith.science/paper/UUMRN73Z"},"agent_actions":{"view_html":"https://pith.science/pith/UUMRN73ZDQJXHVBHWTKHVXRJBG","download_json":"https://pith.science/pith/UUMRN73ZDQJXHVBHWTKHVXRJBG.json","view_paper":"https://pith.science/paper/UUMRN73Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.05537&json=true","fetch_graph":"https://pith.science/api/pith-number/UUMRN73ZDQJXHVBHWTKHVXRJBG/graph.json","fetch_events":"https://pith.science/api/pith-number/UUMRN73ZDQJXHVBHWTKHVXRJBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UUMRN73ZDQJXHVBHWTKHVXRJBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UUMRN73ZDQJXHVBHWTKHVXRJBG/action/storage_attestation","attest_author":"https://pith.science/pith/UUMRN73ZDQJXHVBHWTKHVXRJBG/action/author_attestation","sign_citation":"https://pith.science/pith/UUMRN73ZDQJXHVBHWTKHVXRJBG/action/citation_signature","submit_replication":"https://pith.science/pith/UUMRN73ZDQJXHVBHWTKHVXRJBG/action/replication_record"}},"created_at":"2026-07-05T02:42:02.174885+00:00","updated_at":"2026-07-05T02:42:02.174885+00:00"}