{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:VZU3UPCROLRERZOXT2B223HZ4S","short_pith_number":"pith:VZU3UPCR","schema_version":"1.0","canonical_sha256":"ae69ba3c5172e248e5d79e83ad6cf9e495cc6a9fa6e792e85a1db0f9013eac4e","source":{"kind":"arxiv","id":"1611.04482","version":1},"attestation_state":"computed","paper":{"title":"Practical Secure Aggregation for Federated Learning on User-Held Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CR","authors_text":"Aaron Segal, Antonio Marcedone, Ben Kreuter, Daniel Ramage, H. Brendan McMahan, Karn Seth, Keith Bonawitz, Sarvar Patel, Vladimir Ivanov","submitted_at":"2016-11-14T17:14:55Z","abstract_excerpt":"Secure Aggregation protocols allow a collection of mutually distrust parties, each holding a private value, to collaboratively compute the sum of those values without revealing the values themselves. We consider training a deep neural network in the Federated Learning model, using distributed stochastic gradient descent across user-held training data on mobile devices, wherein Secure Aggregation protects each user's model gradient. We design a novel, communication-efficient Secure Aggregation protocol for high-dimensional data that tolerates up to 1/3 users failing to complete the protocol. Fo"},"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":"1611.04482","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2016-11-14T17:14:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d628e95c9c89ad1948b99bd38549a1cb7a78dd89dc97aa9dcd2b77d9b12f6f77","abstract_canon_sha256":"e31f70b2dd97f073dc1b7d6a6d245f70aacb9c04cb9929b20efa1ccba35dc4ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:58:50.476770Z","signature_b64":"6YArS3ddSSGGN9+JDzYNpQh43+zjbxAcyBhmko7p0fHjiBN8imHOyg5P8U05VipAbhBAFqBGV44ksmFij4O4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae69ba3c5172e248e5d79e83ad6cf9e495cc6a9fa6e792e85a1db0f9013eac4e","last_reissued_at":"2026-05-18T00:58:50.476114Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:58:50.476114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Practical Secure Aggregation for Federated Learning on User-Held Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CR","authors_text":"Aaron Segal, Antonio Marcedone, Ben Kreuter, Daniel Ramage, H. Brendan McMahan, Karn Seth, Keith Bonawitz, Sarvar Patel, Vladimir Ivanov","submitted_at":"2016-11-14T17:14:55Z","abstract_excerpt":"Secure Aggregation protocols allow a collection of mutually distrust parties, each holding a private value, to collaboratively compute the sum of those values without revealing the values themselves. We consider training a deep neural network in the Federated Learning model, using distributed stochastic gradient descent across user-held training data on mobile devices, wherein Secure Aggregation protects each user's model gradient. We design a novel, communication-efficient Secure Aggregation protocol for high-dimensional data that tolerates up to 1/3 users failing to complete the protocol. Fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.04482","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1611.04482","created_at":"2026-05-18T00:58:50.476216+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.04482v1","created_at":"2026-05-18T00:58:50.476216+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.04482","created_at":"2026-05-18T00:58:50.476216+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZU3UPCROLRE","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZU3UPCROLRERZOX","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZU3UPCR","created_at":"2026-05-18T12:30:48.956258+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":10,"sample":[{"citing_arxiv_id":"2411.11707","citing_title":"Federated Co-tuning Framework for Large and Small Language Models","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2501.12709","citing_title":"Experimentally validated quantum-secure federated learning over a multi-user quantum network","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20975","citing_title":"Choose Wisely and Privately: Proactive Client Selection for Fair and Efficient Federated Learning","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22261","citing_title":"Information-Theoretic Decentralized Secure Aggregation with User Dropouts","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2506.05640","citing_title":"FedShield-LLM: A Secure and Scalable Federated Fine-Tuned Large Language Model","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2601.00418","citing_title":"Secure, Verifiable, and Scalable Multi-Client Data Sharing via Consensus-Based Privacy-Preserving Data Distribution","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20975","citing_title":"Choose Wisely and Privately: Proactive Client Selection for Fair and Efficient Federated Learning","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2602.09520","citing_title":"Rashomon Sets and Model Multiplicity in Federated Learning","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00011","citing_title":"FedACT: Concurrent Federated Intelligence across Heterogeneous Data Sources","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13434","citing_title":"Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04103","citing_title":"Compliance-by-Construction Argument Graphs: Using Generative AI to Produce Evidence-Linked Formal Arguments for Certification-Grade Accountability","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11010","citing_title":"A Comparative Study of Federated Learning Aggregation Strategies under Homogeneous and Heterogeneous Data Distributions","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26391","citing_title":"Multi-Server Secure Aggregation with Arbitrary Collusion and Heterogeneous Security Constraints","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08288","citing_title":"UMEDA: Unified Multi-modal Efficient Data Fusion for Privacy-Preserving Graph Federated Learning via Spectral-Gated Attention and Diffusion-Based Operator Alignment","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VZU3UPCROLRERZOXT2B223HZ4S","json":"https://pith.science/pith/VZU3UPCROLRERZOXT2B223HZ4S.json","graph_json":"https://pith.science/api/pith-number/VZU3UPCROLRERZOXT2B223HZ4S/graph.json","events_json":"https://pith.science/api/pith-number/VZU3UPCROLRERZOXT2B223HZ4S/events.json","paper":"https://pith.science/paper/VZU3UPCR"},"agent_actions":{"view_html":"https://pith.science/pith/VZU3UPCROLRERZOXT2B223HZ4S","download_json":"https://pith.science/pith/VZU3UPCROLRERZOXT2B223HZ4S.json","view_paper":"https://pith.science/paper/VZU3UPCR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.04482&json=true","fetch_graph":"https://pith.science/api/pith-number/VZU3UPCROLRERZOXT2B223HZ4S/graph.json","fetch_events":"https://pith.science/api/pith-number/VZU3UPCROLRERZOXT2B223HZ4S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZU3UPCROLRERZOXT2B223HZ4S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZU3UPCROLRERZOXT2B223HZ4S/action/storage_attestation","attest_author":"https://pith.science/pith/VZU3UPCROLRERZOXT2B223HZ4S/action/author_attestation","sign_citation":"https://pith.science/pith/VZU3UPCROLRERZOXT2B223HZ4S/action/citation_signature","submit_replication":"https://pith.science/pith/VZU3UPCROLRERZOXT2B223HZ4S/action/replication_record"}},"created_at":"2026-05-18T00:58:50.476216+00:00","updated_at":"2026-05-18T00:58:50.476216+00:00"}