{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7NC7LXDJFJM2VSN6C5J5SLJ4AL","short_pith_number":"pith:7NC7LXDJ","schema_version":"1.0","canonical_sha256":"fb45f5dc692a59aac9be1753d92d3c02ee0b39ea5a7b20b3bff1ed65b5d85c32","source":{"kind":"arxiv","id":"2210.01437","version":2},"attestation_state":"computed","paper":{"title":"Shielding Federated Learning: Mitigating Byzantine Attacks with Less Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Jianrong Lu, Junyu Shi, Leo Yu Zhang, Man Zhou, Minghui Li, Shengshan Hu, Wei Wan, Yifeng Zheng","submitted_at":"2022-10-04T07:48:19Z","abstract_excerpt":"Federated learning is a newly emerging distributed learning framework that facilitates the collaborative training of a shared global model among distributed participants with their privacy preserved. However, federated learning systems are vulnerable to Byzantine attacks from malicious participants, who can upload carefully crafted local model updates to degrade the quality of the global model and even leave a backdoor. While this problem has received significant attention recently, current defensive schemes heavily rely on various assumptions, such as a fixed Byzantine model, availability of "},"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":"2210.01437","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2022-10-04T07:48:19Z","cross_cats_sorted":[],"title_canon_sha256":"8915d4e4830c26a0d56a059748f9588d8b0bde973273d17f00aa975134c9b601","abstract_canon_sha256":"e939fb0c2adc1fc2d019d0d8c9d751dff1b0d56b4e124db6a2f985afcf920d20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:14.943326Z","signature_b64":"ZeIu2DGX0HTpj1MNJxBJcFv0jWlP2JTMfwe8U8W2EfMbkVOLhKpAQDz3SrvHcBQ3PgcO2O4N59HuiWNresBxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb45f5dc692a59aac9be1753d92d3c02ee0b39ea5a7b20b3bff1ed65b5d85c32","last_reissued_at":"2026-07-05T05:06:14.942842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:14.942842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shielding Federated Learning: Mitigating Byzantine Attacks with Less Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Jianrong Lu, Junyu Shi, Leo Yu Zhang, Man Zhou, Minghui Li, Shengshan Hu, Wei Wan, Yifeng Zheng","submitted_at":"2022-10-04T07:48:19Z","abstract_excerpt":"Federated learning is a newly emerging distributed learning framework that facilitates the collaborative training of a shared global model among distributed participants with their privacy preserved. However, federated learning systems are vulnerable to Byzantine attacks from malicious participants, who can upload carefully crafted local model updates to degrade the quality of the global model and even leave a backdoor. While this problem has received significant attention recently, current defensive schemes heavily rely on various assumptions, such as a fixed Byzantine model, availability of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.01437","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/2210.01437/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":"2210.01437","created_at":"2026-07-05T05:06:14.942900+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.01437v2","created_at":"2026-07-05T05:06:14.942900+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.01437","created_at":"2026-07-05T05:06:14.942900+00:00"},{"alias_kind":"pith_short_12","alias_value":"7NC7LXDJFJM2","created_at":"2026-07-05T05:06:14.942900+00:00"},{"alias_kind":"pith_short_16","alias_value":"7NC7LXDJFJM2VSN6","created_at":"2026-07-05T05:06:14.942900+00:00"},{"alias_kind":"pith_short_8","alias_value":"7NC7LXDJ","created_at":"2026-07-05T05:06:14.942900+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/7NC7LXDJFJM2VSN6C5J5SLJ4AL","json":"https://pith.science/pith/7NC7LXDJFJM2VSN6C5J5SLJ4AL.json","graph_json":"https://pith.science/api/pith-number/7NC7LXDJFJM2VSN6C5J5SLJ4AL/graph.json","events_json":"https://pith.science/api/pith-number/7NC7LXDJFJM2VSN6C5J5SLJ4AL/events.json","paper":"https://pith.science/paper/7NC7LXDJ"},"agent_actions":{"view_html":"https://pith.science/pith/7NC7LXDJFJM2VSN6C5J5SLJ4AL","download_json":"https://pith.science/pith/7NC7LXDJFJM2VSN6C5J5SLJ4AL.json","view_paper":"https://pith.science/paper/7NC7LXDJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.01437&json=true","fetch_graph":"https://pith.science/api/pith-number/7NC7LXDJFJM2VSN6C5J5SLJ4AL/graph.json","fetch_events":"https://pith.science/api/pith-number/7NC7LXDJFJM2VSN6C5J5SLJ4AL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7NC7LXDJFJM2VSN6C5J5SLJ4AL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7NC7LXDJFJM2VSN6C5J5SLJ4AL/action/storage_attestation","attest_author":"https://pith.science/pith/7NC7LXDJFJM2VSN6C5J5SLJ4AL/action/author_attestation","sign_citation":"https://pith.science/pith/7NC7LXDJFJM2VSN6C5J5SLJ4AL/action/citation_signature","submit_replication":"https://pith.science/pith/7NC7LXDJFJM2VSN6C5J5SLJ4AL/action/replication_record"}},"created_at":"2026-07-05T05:06:14.942900+00:00","updated_at":"2026-07-05T05:06:14.942900+00:00"}