{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3SZBK4LTIPGVDYYBE6IU2NXCME","short_pith_number":"pith:3SZBK4LT","schema_version":"1.0","canonical_sha256":"dcb215717343cd51e30127914d36e26127080e68a55ee7190a4a5b4e2800b10e","source":{"kind":"arxiv","id":"2502.02038","version":2},"attestation_state":"computed","paper":{"title":"SMTFL: Secure Model Training to Untrusted Participants in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.CR","authors_text":"Dan Yu, Hongsong Zhu, Jianhua Wang, Xiaorong Dong, Yimo Ren, Yongle Chen, Zhihui Zhao","submitted_at":"2025-02-04T06:12:43Z","abstract_excerpt":"Federated learning is an essential distributed model training technique. However, threats such as gradient inversion attacks and poisoning attacks pose significant risks to the privacy of training data and the model correctness. We propose a novel approach called SMTFL to achieve secure model training in federated learning without relying on trusted participants. To safeguard gradients privacy against gradient inversion attacks, clients are dynamically grouped, allowing one client's gradient to be divided to obfuscate the gradients of other clients within the group. This method incorporates ch"},"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":"2502.02038","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-02-04T06:12:43Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"121b1b626414a4f3ad7400cdcc85c2e5a5ab40f800946ee4cb9d24e60a619046","abstract_canon_sha256":"4a2a895e629e31c507828d3f6e88d88815cf5619516c6fdbc172adc9d204895c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:53.656660Z","signature_b64":"6s5Tob5gCO5csq9N004F5zui6HDbEG0Bu/TU9g7Xi8C5qsv3EmYT4+zVfTG89SuO+RgtUceDcAxIgZuGUDQ7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcb215717343cd51e30127914d36e26127080e68a55ee7190a4a5b4e2800b10e","last_reissued_at":"2026-07-05T10:17:53.656169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:53.656169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SMTFL: Secure Model Training to Untrusted Participants in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.CR","authors_text":"Dan Yu, Hongsong Zhu, Jianhua Wang, Xiaorong Dong, Yimo Ren, Yongle Chen, Zhihui Zhao","submitted_at":"2025-02-04T06:12:43Z","abstract_excerpt":"Federated learning is an essential distributed model training technique. However, threats such as gradient inversion attacks and poisoning attacks pose significant risks to the privacy of training data and the model correctness. We propose a novel approach called SMTFL to achieve secure model training in federated learning without relying on trusted participants. To safeguard gradients privacy against gradient inversion attacks, clients are dynamically grouped, allowing one client's gradient to be divided to obfuscate the gradients of other clients within the group. This method incorporates ch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02038","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/2502.02038/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":"2502.02038","created_at":"2026-07-05T10:17:53.656238+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02038v2","created_at":"2026-07-05T10:17:53.656238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02038","created_at":"2026-07-05T10:17:53.656238+00:00"},{"alias_kind":"pith_short_12","alias_value":"3SZBK4LTIPGV","created_at":"2026-07-05T10:17:53.656238+00:00"},{"alias_kind":"pith_short_16","alias_value":"3SZBK4LTIPGVDYYB","created_at":"2026-07-05T10:17:53.656238+00:00"},{"alias_kind":"pith_short_8","alias_value":"3SZBK4LT","created_at":"2026-07-05T10:17:53.656238+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05943","citing_title":"SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3SZBK4LTIPGVDYYBE6IU2NXCME","json":"https://pith.science/pith/3SZBK4LTIPGVDYYBE6IU2NXCME.json","graph_json":"https://pith.science/api/pith-number/3SZBK4LTIPGVDYYBE6IU2NXCME/graph.json","events_json":"https://pith.science/api/pith-number/3SZBK4LTIPGVDYYBE6IU2NXCME/events.json","paper":"https://pith.science/paper/3SZBK4LT"},"agent_actions":{"view_html":"https://pith.science/pith/3SZBK4LTIPGVDYYBE6IU2NXCME","download_json":"https://pith.science/pith/3SZBK4LTIPGVDYYBE6IU2NXCME.json","view_paper":"https://pith.science/paper/3SZBK4LT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02038&json=true","fetch_graph":"https://pith.science/api/pith-number/3SZBK4LTIPGVDYYBE6IU2NXCME/graph.json","fetch_events":"https://pith.science/api/pith-number/3SZBK4LTIPGVDYYBE6IU2NXCME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3SZBK4LTIPGVDYYBE6IU2NXCME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3SZBK4LTIPGVDYYBE6IU2NXCME/action/storage_attestation","attest_author":"https://pith.science/pith/3SZBK4LTIPGVDYYBE6IU2NXCME/action/author_attestation","sign_citation":"https://pith.science/pith/3SZBK4LTIPGVDYYBE6IU2NXCME/action/citation_signature","submit_replication":"https://pith.science/pith/3SZBK4LTIPGVDYYBE6IU2NXCME/action/replication_record"}},"created_at":"2026-07-05T10:17:53.656238+00:00","updated_at":"2026-07-05T10:17:53.656238+00:00"}