{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TDZD4MFEVBBA53AUA3MFZOG7GW","short_pith_number":"pith:TDZD4MFE","schema_version":"1.0","canonical_sha256":"98f23e30a4a8420eec1406d85cb8df35a5996279c139fc6cd47fc90251e766db","source":{"kind":"arxiv","id":"2405.07708","version":2},"attestation_state":"computed","paper":{"title":"Secure Aggregation Meets Sparsification in Decentralized Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anne-Marie Kermarrec, Milos Vujasinovic, Rafael Pires, Rishi Sharma, Sayan Biswas","submitted_at":"2024-05-13T12:52:58Z","abstract_excerpt":"Decentralized learning (DL) faces increased vulnerability to privacy breaches due to sophisticated attacks on machine learning (ML) models. Secure aggregation is a computationally efficient cryptographic technique that enables multiple parties to compute an aggregate of their private data while keeping their individual inputs concealed from each other and from any central aggregator. To enhance communication efficiency in DL, sparsification techniques are used, selectively sharing only the most crucial parameters or gradients in a model, thereby maintaining efficiency without notably compromis"},"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":"2405.07708","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-13T12:52:58Z","cross_cats_sorted":[],"title_canon_sha256":"e9523141ad58e6adc460aa8fd9a6aca9ccda5f29efe181c4ba979288cdf43772","abstract_canon_sha256":"2a50f53c1e2afba561fa7dc08eccded3f2e1951f47b4c6af38b16dd1bc68ff91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:53.624824Z","signature_b64":"Yw9FVkUo7Lsq8vFBUsAfCDJoQsdKK+AYhJwuOHdSm7AdHoKX4nspigQffoXEIbm0+XDbsQZwPHheDVl2LuQyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98f23e30a4a8420eec1406d85cb8df35a5996279c139fc6cd47fc90251e766db","last_reissued_at":"2026-07-05T08:18:53.624345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:53.624345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Secure Aggregation Meets Sparsification in Decentralized Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anne-Marie Kermarrec, Milos Vujasinovic, Rafael Pires, Rishi Sharma, Sayan Biswas","submitted_at":"2024-05-13T12:52:58Z","abstract_excerpt":"Decentralized learning (DL) faces increased vulnerability to privacy breaches due to sophisticated attacks on machine learning (ML) models. Secure aggregation is a computationally efficient cryptographic technique that enables multiple parties to compute an aggregate of their private data while keeping their individual inputs concealed from each other and from any central aggregator. To enhance communication efficiency in DL, sparsification techniques are used, selectively sharing only the most crucial parameters or gradients in a model, thereby maintaining efficiency without notably compromis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.07708","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/2405.07708/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":"2405.07708","created_at":"2026-07-05T08:18:53.624404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.07708v2","created_at":"2026-07-05T08:18:53.624404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.07708","created_at":"2026-07-05T08:18:53.624404+00:00"},{"alias_kind":"pith_short_12","alias_value":"TDZD4MFEVBBA","created_at":"2026-07-05T08:18:53.624404+00:00"},{"alias_kind":"pith_short_16","alias_value":"TDZD4MFEVBBA53AU","created_at":"2026-07-05T08:18:53.624404+00:00"},{"alias_kind":"pith_short_8","alias_value":"TDZD4MFE","created_at":"2026-07-05T08:18:53.624404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.19969","citing_title":"Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learning","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19969","citing_title":"Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learning","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TDZD4MFEVBBA53AUA3MFZOG7GW","json":"https://pith.science/pith/TDZD4MFEVBBA53AUA3MFZOG7GW.json","graph_json":"https://pith.science/api/pith-number/TDZD4MFEVBBA53AUA3MFZOG7GW/graph.json","events_json":"https://pith.science/api/pith-number/TDZD4MFEVBBA53AUA3MFZOG7GW/events.json","paper":"https://pith.science/paper/TDZD4MFE"},"agent_actions":{"view_html":"https://pith.science/pith/TDZD4MFEVBBA53AUA3MFZOG7GW","download_json":"https://pith.science/pith/TDZD4MFEVBBA53AUA3MFZOG7GW.json","view_paper":"https://pith.science/paper/TDZD4MFE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.07708&json=true","fetch_graph":"https://pith.science/api/pith-number/TDZD4MFEVBBA53AUA3MFZOG7GW/graph.json","fetch_events":"https://pith.science/api/pith-number/TDZD4MFEVBBA53AUA3MFZOG7GW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TDZD4MFEVBBA53AUA3MFZOG7GW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TDZD4MFEVBBA53AUA3MFZOG7GW/action/storage_attestation","attest_author":"https://pith.science/pith/TDZD4MFEVBBA53AUA3MFZOG7GW/action/author_attestation","sign_citation":"https://pith.science/pith/TDZD4MFEVBBA53AUA3MFZOG7GW/action/citation_signature","submit_replication":"https://pith.science/pith/TDZD4MFEVBBA53AUA3MFZOG7GW/action/replication_record"}},"created_at":"2026-07-05T08:18:53.624404+00:00","updated_at":"2026-07-05T08:18:53.624404+00:00"}