{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DJSPL6CYLFHW22ZBAEIQ7AUCMA","short_pith_number":"pith:DJSPL6CY","schema_version":"1.0","canonical_sha256":"1a64f5f858594f6d6b2101110f82826011213ef65af4cfc1c75ab28c880bb1cf","source":{"kind":"arxiv","id":"2506.15181","version":1},"attestation_state":"computed","paper":{"title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bing Liu, Chengcheng Zhao, Li Chai, Peng Cheng, Yaonan Wang","submitted_at":"2025-06-18T06:53:52Z","abstract_excerpt":"Jointly addressing Byzantine attacks and privacy leakage in distributed machine learning (DML) has become an important issue. A common strategy involves integrating Byzantine-resilient aggregation rules with differential privacy mechanisms. However, the incorporation of these techniques often results in a significant degradation in model accuracy. To address this issue, we propose a decentralized DML framework, named ImprovDML, that achieves high model accuracy while simultaneously ensuring privacy preservation and resilience to Byzantine attacks. The framework leverages a kind of resilient ve"},"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":"2506.15181","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T06:53:52Z","cross_cats_sorted":[],"title_canon_sha256":"92514db42f8508756262a58ebbbbdd02b12c44cf2e9172ac7db1570ad996e5d6","abstract_canon_sha256":"2dcf636fb06b2ae3a7efed1b40fd34780e9beb4838d2a81ba8e67f4ec3bba491"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:38.660365Z","signature_b64":"nwR3Njqrdt/N5HopuJPwdl1MCV/FwKaBd16pXZKT6cfgkcWoZWeAdo5A9aFLeTM0Cz1jJ8pOVHAR8da+Ur4FCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a64f5f858594f6d6b2101110f82826011213ef65af4cfc1c75ab28c880bb1cf","last_reissued_at":"2026-07-05T11:23:38.659848Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:38.659848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bing Liu, Chengcheng Zhao, Li Chai, Peng Cheng, Yaonan Wang","submitted_at":"2025-06-18T06:53:52Z","abstract_excerpt":"Jointly addressing Byzantine attacks and privacy leakage in distributed machine learning (DML) has become an important issue. A common strategy involves integrating Byzantine-resilient aggregation rules with differential privacy mechanisms. However, the incorporation of these techniques often results in a significant degradation in model accuracy. To address this issue, we propose a decentralized DML framework, named ImprovDML, that achieves high model accuracy while simultaneously ensuring privacy preservation and resilience to Byzantine attacks. The framework leverages a kind of resilient ve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15181","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.15181/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":"2506.15181","created_at":"2026-07-05T11:23:38.659907+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.15181v1","created_at":"2026-07-05T11:23:38.659907+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15181","created_at":"2026-07-05T11:23:38.659907+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJSPL6CYLFHW","created_at":"2026-07-05T11:23:38.659907+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJSPL6CYLFHW22ZB","created_at":"2026-07-05T11:23:38.659907+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJSPL6CY","created_at":"2026-07-05T11:23:38.659907+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DJSPL6CYLFHW22ZBAEIQ7AUCMA","json":"https://pith.science/pith/DJSPL6CYLFHW22ZBAEIQ7AUCMA.json","graph_json":"https://pith.science/api/pith-number/DJSPL6CYLFHW22ZBAEIQ7AUCMA/graph.json","events_json":"https://pith.science/api/pith-number/DJSPL6CYLFHW22ZBAEIQ7AUCMA/events.json","paper":"https://pith.science/paper/DJSPL6CY"},"agent_actions":{"view_html":"https://pith.science/pith/DJSPL6CYLFHW22ZBAEIQ7AUCMA","download_json":"https://pith.science/pith/DJSPL6CYLFHW22ZBAEIQ7AUCMA.json","view_paper":"https://pith.science/paper/DJSPL6CY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.15181&json=true","fetch_graph":"https://pith.science/api/pith-number/DJSPL6CYLFHW22ZBAEIQ7AUCMA/graph.json","fetch_events":"https://pith.science/api/pith-number/DJSPL6CYLFHW22ZBAEIQ7AUCMA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJSPL6CYLFHW22ZBAEIQ7AUCMA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJSPL6CYLFHW22ZBAEIQ7AUCMA/action/storage_attestation","attest_author":"https://pith.science/pith/DJSPL6CYLFHW22ZBAEIQ7AUCMA/action/author_attestation","sign_citation":"https://pith.science/pith/DJSPL6CYLFHW22ZBAEIQ7AUCMA/action/citation_signature","submit_replication":"https://pith.science/pith/DJSPL6CYLFHW22ZBAEIQ7AUCMA/action/replication_record"}},"created_at":"2026-07-05T11:23:38.659907+00:00","updated_at":"2026-07-05T11:23:38.659907+00:00"}