{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JSAAMTGNY2XWXSI3MJSAMH7KFF","short_pith_number":"pith:JSAAMTGN","schema_version":"1.0","canonical_sha256":"4c80064ccdc6af6bc91b6264061fea2960cd4a1903d010b785e424c023e0c477","source":{"kind":"arxiv","id":"2402.07471","version":2},"attestation_state":"computed","paper":{"title":"Differentially Private Decentralized Learning with Random Walks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Aur\\'elien Bellet, Edwige Cyffers, Jalaj Upadhyay","submitted_at":"2024-02-12T08:16:58Z","abstract_excerpt":"The popularity of federated learning comes from the possibility of better scalability and the ability for participants to keep control of their data, improving data security and sovereignty. Unfortunately, sharing model updates also creates a new privacy attack surface. In this work, we characterize the privacy guarantees of decentralized learning with random walk algorithms, where a model is updated by traveling from one node to another along the edges of a communication graph. Using a recent variant of differential privacy tailored to the study of decentralized algorithms, namely Pairwise Ne"},"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":"2402.07471","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-12T08:16:58Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"cdc4499c370f90a1121d1bfa1074fbb6c5f51df1f2e57fb094ebe143766458ca","abstract_canon_sha256":"3ff5e8765895799e2413d124a3d4c222781879649e1baac9d13b6405a216558f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:03.528189Z","signature_b64":"AFAKLQG6MPzgYTncOJsc8uWUvUDt/2ukigPfWAJmFSApuqYhrO426NXHdF2k6pOhZtO+q6H7rXMOYDnCnqLFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c80064ccdc6af6bc91b6264061fea2960cd4a1903d010b785e424c023e0c477","last_reissued_at":"2026-07-05T08:27:03.527693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:03.527693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentially Private Decentralized Learning with Random Walks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Aur\\'elien Bellet, Edwige Cyffers, Jalaj Upadhyay","submitted_at":"2024-02-12T08:16:58Z","abstract_excerpt":"The popularity of federated learning comes from the possibility of better scalability and the ability for participants to keep control of their data, improving data security and sovereignty. Unfortunately, sharing model updates also creates a new privacy attack surface. In this work, we characterize the privacy guarantees of decentralized learning with random walk algorithms, where a model is updated by traveling from one node to another along the edges of a communication graph. Using a recent variant of differential privacy tailored to the study of decentralized algorithms, namely Pairwise Ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07471","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/2402.07471/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":"2402.07471","created_at":"2026-07-05T08:27:03.527761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.07471v2","created_at":"2026-07-05T08:27:03.527761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07471","created_at":"2026-07-05T08:27:03.527761+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSAAMTGNY2XW","created_at":"2026-07-05T08:27:03.527761+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSAAMTGNY2XWXSI3","created_at":"2026-07-05T08:27:03.527761+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSAAMTGN","created_at":"2026-07-05T08:27:03.527761+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03746","citing_title":"Dropout-Robust Mechanisms for Differentially Private and Fully Decentralized Mean Estimation","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JSAAMTGNY2XWXSI3MJSAMH7KFF","json":"https://pith.science/pith/JSAAMTGNY2XWXSI3MJSAMH7KFF.json","graph_json":"https://pith.science/api/pith-number/JSAAMTGNY2XWXSI3MJSAMH7KFF/graph.json","events_json":"https://pith.science/api/pith-number/JSAAMTGNY2XWXSI3MJSAMH7KFF/events.json","paper":"https://pith.science/paper/JSAAMTGN"},"agent_actions":{"view_html":"https://pith.science/pith/JSAAMTGNY2XWXSI3MJSAMH7KFF","download_json":"https://pith.science/pith/JSAAMTGNY2XWXSI3MJSAMH7KFF.json","view_paper":"https://pith.science/paper/JSAAMTGN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.07471&json=true","fetch_graph":"https://pith.science/api/pith-number/JSAAMTGNY2XWXSI3MJSAMH7KFF/graph.json","fetch_events":"https://pith.science/api/pith-number/JSAAMTGNY2XWXSI3MJSAMH7KFF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSAAMTGNY2XWXSI3MJSAMH7KFF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSAAMTGNY2XWXSI3MJSAMH7KFF/action/storage_attestation","attest_author":"https://pith.science/pith/JSAAMTGNY2XWXSI3MJSAMH7KFF/action/author_attestation","sign_citation":"https://pith.science/pith/JSAAMTGNY2XWXSI3MJSAMH7KFF/action/citation_signature","submit_replication":"https://pith.science/pith/JSAAMTGNY2XWXSI3MJSAMH7KFF/action/replication_record"}},"created_at":"2026-07-05T08:27:03.527761+00:00","updated_at":"2026-07-05T08:27:03.527761+00:00"}