{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4YWEV3FQFHDIIRARG23FSTELN5","short_pith_number":"pith:4YWEV3FQ","schema_version":"1.0","canonical_sha256":"e62c4aecb029c684441136b6594c8b6f708e7e3107d2bbfb81e44a75b99a29e9","source":{"kind":"arxiv","id":"2404.10764","version":2},"attestation_state":"computed","paper":{"title":"Confidential Federated Computations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Adria Gascon, Albert Cheu, Brendan McMahan, Brett McLarnon, Daniel Ramage, Dzmitry Huba, Hubert Eichner, Kallista Bonawitz, Katharine Daly, Marco Gruteser, Nova Fallen, Peter Kairouz, Timon Van Overveldt, Tiziano Santoro","submitted_at":"2024-04-16T17:47:27Z","abstract_excerpt":"Federated Learning and Analytics (FLA) have seen widespread adoption by technology platforms for processing sensitive on-device data. However, basic FLA systems have privacy limitations: they do not necessarily require anonymization mechanisms like differential privacy (DP), and provide limited protections against a potentially malicious service provider. Adding DP to a basic FLA system currently requires either adding excessive noise to each device's updates, or assuming an honest service provider that correctly implements the mechanism and only uses the privatized outputs. Secure multiparty "},"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":"2404.10764","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-04-16T17:47:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"53eea8ec538f58dfdb8501474dd2a38fa799be7d14182803b4221e3a54213d60","abstract_canon_sha256":"598e17b4373f36e1b8222afb9f3bb2e9bbcaa2d2c3f311ae27a49f25af21bc99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:45.453956Z","signature_b64":"U2qd1RnN7jQyoWbR72wBoO24fuSfEzJaVWROfMDa0v5WFBuCil9nQioOynoCBgxGWParbOPau4c4b8A6u21wBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e62c4aecb029c684441136b6594c8b6f708e7e3107d2bbfb81e44a75b99a29e9","last_reissued_at":"2026-07-05T10:22:45.453207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:45.453207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Confidential Federated Computations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Adria Gascon, Albert Cheu, Brendan McMahan, Brett McLarnon, Daniel Ramage, Dzmitry Huba, Hubert Eichner, Kallista Bonawitz, Katharine Daly, Marco Gruteser, Nova Fallen, Peter Kairouz, Timon Van Overveldt, Tiziano Santoro","submitted_at":"2024-04-16T17:47:27Z","abstract_excerpt":"Federated Learning and Analytics (FLA) have seen widespread adoption by technology platforms for processing sensitive on-device data. However, basic FLA systems have privacy limitations: they do not necessarily require anonymization mechanisms like differential privacy (DP), and provide limited protections against a potentially malicious service provider. Adding DP to a basic FLA system currently requires either adding excessive noise to each device's updates, or assuming an honest service provider that correctly implements the mechanism and only uses the privatized outputs. Secure multiparty "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10764","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/2404.10764/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":"2404.10764","created_at":"2026-07-05T10:22:45.453323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.10764v2","created_at":"2026-07-05T10:22:45.453323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10764","created_at":"2026-07-05T10:22:45.453323+00:00"},{"alias_kind":"pith_short_12","alias_value":"4YWEV3FQFHDI","created_at":"2026-07-05T10:22:45.453323+00:00"},{"alias_kind":"pith_short_16","alias_value":"4YWEV3FQFHDIIRAR","created_at":"2026-07-05T10:22:45.453323+00:00"},{"alias_kind":"pith_short_8","alias_value":"4YWEV3FQ","created_at":"2026-07-05T10:22:45.453323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04899","citing_title":"DIST-FL: Enhancing Security for TEE-based Aggregation in Federated Learning","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02958","citing_title":"Echelon: Auditable Aggregate-Only Language-Model Adaptation Across Privacy Boundaries","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15573","citing_title":"Response-Conditioned Parallel-to-Sequential Orchestration for Multi-Agent Systems","ref_index":150,"is_internal_anchor":false},{"citing_arxiv_id":"2507.02770","citing_title":"Blueprint, Bootstrap, and Bridge: A Security Look at NVIDIA GPU Confidential Computing","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4YWEV3FQFHDIIRARG23FSTELN5","json":"https://pith.science/pith/4YWEV3FQFHDIIRARG23FSTELN5.json","graph_json":"https://pith.science/api/pith-number/4YWEV3FQFHDIIRARG23FSTELN5/graph.json","events_json":"https://pith.science/api/pith-number/4YWEV3FQFHDIIRARG23FSTELN5/events.json","paper":"https://pith.science/paper/4YWEV3FQ"},"agent_actions":{"view_html":"https://pith.science/pith/4YWEV3FQFHDIIRARG23FSTELN5","download_json":"https://pith.science/pith/4YWEV3FQFHDIIRARG23FSTELN5.json","view_paper":"https://pith.science/paper/4YWEV3FQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.10764&json=true","fetch_graph":"https://pith.science/api/pith-number/4YWEV3FQFHDIIRARG23FSTELN5/graph.json","fetch_events":"https://pith.science/api/pith-number/4YWEV3FQFHDIIRARG23FSTELN5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4YWEV3FQFHDIIRARG23FSTELN5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4YWEV3FQFHDIIRARG23FSTELN5/action/storage_attestation","attest_author":"https://pith.science/pith/4YWEV3FQFHDIIRARG23FSTELN5/action/author_attestation","sign_citation":"https://pith.science/pith/4YWEV3FQFHDIIRARG23FSTELN5/action/citation_signature","submit_replication":"https://pith.science/pith/4YWEV3FQFHDIIRARG23FSTELN5/action/replication_record"}},"created_at":"2026-07-05T10:22:45.453323+00:00","updated_at":"2026-07-05T10:22:45.453323+00:00"}