{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:J2PHO3OJNBFOBIA53PG6MU2ZSW","short_pith_number":"pith:J2PHO3OJ","schema_version":"1.0","canonical_sha256":"4e9e776dc9684ae0a01ddbcde6535995a41296be69016f4f90b37f119009446a","source":{"kind":"arxiv","id":"2012.05433","version":3},"attestation_state":"computed","paper":{"title":"Communication-Computation Efficient Secure Aggregation for Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Beongjun Choi, Dong-Jun Han, Jaekyun Moon, Jy-yong Sohn","submitted_at":"2020-12-10T03:17:50Z","abstract_excerpt":"Federated learning has been spotlighted as a way to train neural networks using distributed data with no need for individual nodes to share data. Unfortunately, it has also been shown that adversaries may be able to extract local data contents off model parameters transmitted during federated learning. A recent solution based on the secure aggregation primitive enabled privacy-preserving federated learning, but at the expense of significant extra communication/computational resources. In this paper, we propose a low-complexity scheme that provides data privacy using substantially reduced commu"},"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":"2012.05433","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-10T03:17:50Z","cross_cats_sorted":["cs.CR","cs.IT","math.IT"],"title_canon_sha256":"b95b3c87269bff2bef48574209f35b0f84e5a337178825cbb52f3f564f0a131f","abstract_canon_sha256":"19ecbc98ab1a17517895fdb4140130a38d659260a7cca979561e6d719b8ea441"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:55.133330Z","signature_b64":"BtwoWl8psgLZdE5uTv/SKj3ihQCFcBSGQQXJEiE/KcYEIJhn4GdcUS0addYpdm8012fSsVPFvgD5Er1YgieNBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e9e776dc9684ae0a01ddbcde6535995a41296be69016f4f90b37f119009446a","last_reissued_at":"2026-07-05T02:56:55.132853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:55.132853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Communication-Computation Efficient Secure Aggregation for Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Beongjun Choi, Dong-Jun Han, Jaekyun Moon, Jy-yong Sohn","submitted_at":"2020-12-10T03:17:50Z","abstract_excerpt":"Federated learning has been spotlighted as a way to train neural networks using distributed data with no need for individual nodes to share data. Unfortunately, it has also been shown that adversaries may be able to extract local data contents off model parameters transmitted during federated learning. A recent solution based on the secure aggregation primitive enabled privacy-preserving federated learning, but at the expense of significant extra communication/computational resources. In this paper, we propose a low-complexity scheme that provides data privacy using substantially reduced commu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05433","kind":"arxiv","version":3},"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/2012.05433/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":"2012.05433","created_at":"2026-07-05T02:56:55.132910+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.05433v3","created_at":"2026-07-05T02:56:55.132910+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05433","created_at":"2026-07-05T02:56:55.132910+00:00"},{"alias_kind":"pith_short_12","alias_value":"J2PHO3OJNBFO","created_at":"2026-07-05T02:56:55.132910+00:00"},{"alias_kind":"pith_short_16","alias_value":"J2PHO3OJNBFOBIA5","created_at":"2026-07-05T02:56:55.132910+00:00"},{"alias_kind":"pith_short_8","alias_value":"J2PHO3OJ","created_at":"2026-07-05T02:56:55.132910+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07277","citing_title":"The Capacity of Information-Theoretic Secure Aggregation in Federated Learning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22261","citing_title":"Information-Theoretic Decentralized Secure Aggregation with User Dropouts","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J2PHO3OJNBFOBIA53PG6MU2ZSW","json":"https://pith.science/pith/J2PHO3OJNBFOBIA53PG6MU2ZSW.json","graph_json":"https://pith.science/api/pith-number/J2PHO3OJNBFOBIA53PG6MU2ZSW/graph.json","events_json":"https://pith.science/api/pith-number/J2PHO3OJNBFOBIA53PG6MU2ZSW/events.json","paper":"https://pith.science/paper/J2PHO3OJ"},"agent_actions":{"view_html":"https://pith.science/pith/J2PHO3OJNBFOBIA53PG6MU2ZSW","download_json":"https://pith.science/pith/J2PHO3OJNBFOBIA53PG6MU2ZSW.json","view_paper":"https://pith.science/paper/J2PHO3OJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.05433&json=true","fetch_graph":"https://pith.science/api/pith-number/J2PHO3OJNBFOBIA53PG6MU2ZSW/graph.json","fetch_events":"https://pith.science/api/pith-number/J2PHO3OJNBFOBIA53PG6MU2ZSW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J2PHO3OJNBFOBIA53PG6MU2ZSW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J2PHO3OJNBFOBIA53PG6MU2ZSW/action/storage_attestation","attest_author":"https://pith.science/pith/J2PHO3OJNBFOBIA53PG6MU2ZSW/action/author_attestation","sign_citation":"https://pith.science/pith/J2PHO3OJNBFOBIA53PG6MU2ZSW/action/citation_signature","submit_replication":"https://pith.science/pith/J2PHO3OJNBFOBIA53PG6MU2ZSW/action/replication_record"}},"created_at":"2026-07-05T02:56:55.132910+00:00","updated_at":"2026-07-05T02:56:55.132910+00:00"}