{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5QMYTBCIC6J442D2BN2TJA7CP4","short_pith_number":"pith:5QMYTBCI","schema_version":"1.0","canonical_sha256":"ec198984481793ce687a0b753483e27f1ead173f03d71a9c0d56772c1521176c","source":{"kind":"arxiv","id":"2306.12608","version":4},"attestation_state":"computed","paper":{"title":"DP-BREM: Differentially-Private and Byzantine-Robust Federated Learning with Client Momentum","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Li Xiong, Ming Li, Xiaolan Gu","submitted_at":"2023-06-22T00:11:53Z","abstract_excerpt":"Federated Learning (FL) allows multiple participating clients to train machine learning models collaboratively while keeping their datasets local and only exchanging the gradient or model updates with a coordinating server. Existing FL protocols are vulnerable to attacks that aim to compromise data privacy and/or model robustness. Recently proposed defenses focused on ensuring either privacy or robustness, but not both. In this paper, we focus on simultaneously achieving differential privacy (DP) and Byzantine robustness for cross-silo FL, based on the idea of learning from history. The robust"},"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":"2306.12608","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2023-06-22T00:11:53Z","cross_cats_sorted":[],"title_canon_sha256":"56f2cee17b0c976bc16fe46d3cadecdf7c7272b9437392aa5e58ab1c4c2f822d","abstract_canon_sha256":"159cb4a6d3de785f98342357738171a94833de34bdf3f0a4adbace8c9a5df15b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:59.567885Z","signature_b64":"cXxvY7HU8SjLBSQBQJUHgevw5/jJOVom/YN+KV3sQqlbY1TkUbhHZAzGGhiIIVsi/c45ypTeIQIbye8nx469CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec198984481793ce687a0b753483e27f1ead173f03d71a9c0d56772c1521176c","last_reissued_at":"2026-07-05T09:48:59.567313Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:59.567313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DP-BREM: Differentially-Private and Byzantine-Robust Federated Learning with Client Momentum","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Li Xiong, Ming Li, Xiaolan Gu","submitted_at":"2023-06-22T00:11:53Z","abstract_excerpt":"Federated Learning (FL) allows multiple participating clients to train machine learning models collaboratively while keeping their datasets local and only exchanging the gradient or model updates with a coordinating server. Existing FL protocols are vulnerable to attacks that aim to compromise data privacy and/or model robustness. Recently proposed defenses focused on ensuring either privacy or robustness, but not both. In this paper, we focus on simultaneously achieving differential privacy (DP) and Byzantine robustness for cross-silo FL, based on the idea of learning from history. The robust"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.12608","kind":"arxiv","version":4},"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/2306.12608/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":"2306.12608","created_at":"2026-07-05T09:48:59.567389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.12608v4","created_at":"2026-07-05T09:48:59.567389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.12608","created_at":"2026-07-05T09:48:59.567389+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QMYTBCIC6J4","created_at":"2026-07-05T09:48:59.567389+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QMYTBCIC6J442D2","created_at":"2026-07-05T09:48:59.567389+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QMYTBCI","created_at":"2026-07-05T09:48:59.567389+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28123","citing_title":"Dangerous Liaisons of Convex Learning and Non-Affine Aggregation","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2511.14715","citing_title":"FLARE: Adaptive Multi-Dimensional Reputation for Robust Client Reliability in Federated Learning","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5QMYTBCIC6J442D2BN2TJA7CP4","json":"https://pith.science/pith/5QMYTBCIC6J442D2BN2TJA7CP4.json","graph_json":"https://pith.science/api/pith-number/5QMYTBCIC6J442D2BN2TJA7CP4/graph.json","events_json":"https://pith.science/api/pith-number/5QMYTBCIC6J442D2BN2TJA7CP4/events.json","paper":"https://pith.science/paper/5QMYTBCI"},"agent_actions":{"view_html":"https://pith.science/pith/5QMYTBCIC6J442D2BN2TJA7CP4","download_json":"https://pith.science/pith/5QMYTBCIC6J442D2BN2TJA7CP4.json","view_paper":"https://pith.science/paper/5QMYTBCI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.12608&json=true","fetch_graph":"https://pith.science/api/pith-number/5QMYTBCIC6J442D2BN2TJA7CP4/graph.json","fetch_events":"https://pith.science/api/pith-number/5QMYTBCIC6J442D2BN2TJA7CP4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QMYTBCIC6J442D2BN2TJA7CP4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QMYTBCIC6J442D2BN2TJA7CP4/action/storage_attestation","attest_author":"https://pith.science/pith/5QMYTBCIC6J442D2BN2TJA7CP4/action/author_attestation","sign_citation":"https://pith.science/pith/5QMYTBCIC6J442D2BN2TJA7CP4/action/citation_signature","submit_replication":"https://pith.science/pith/5QMYTBCIC6J442D2BN2TJA7CP4/action/replication_record"}},"created_at":"2026-07-05T09:48:59.567389+00:00","updated_at":"2026-07-05T09:48:59.567389+00:00"}