{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:T2HJMJ7PK6UYZKMHMSPDUTODZE","short_pith_number":"pith:T2HJMJ7P","schema_version":"1.0","canonical_sha256":"9e8e9627ef57a98ca987649e3a4dc3c923dd21c78d1abf33c3dd50878f676c6b","source":{"kind":"arxiv","id":"2201.03772","version":1},"attestation_state":"computed","paper":{"title":"RFLBAT: A Robust Federated Learning Algorithm against Backdoor Attack","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.CR","authors_text":"Dihua Zhai, Yongkang Wang, Yuanqing Xia, Yufeng Zhan","submitted_at":"2022-01-11T04:19:20Z","abstract_excerpt":"Federated learning (FL) is a distributed machine learning paradigm where enormous scattered clients (e.g. mobile devices or IoT devices) collaboratively train a model under the orchestration of a central server (e.g. service provider), while keeping the training data decentralized. Unfortunately, FL is susceptible to a variety of attacks, including backdoor attack, which is made substantially worse in the presence of malicious attackers. Most of algorithms usually assume that the malicious at tackers no more than benign clients or the data distribution is independent identically distribution ("},"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":"2201.03772","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2022-01-11T04:19:20Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"f56980198a954e17fabb78e7ae9184ec3691a6363a85bab33f0917dba24d73d8","abstract_canon_sha256":"b2309ebb615f1593a0e7423552901421a3b3ac87c10582a28de64e7fc6a63acc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:47:33.216040Z","signature_b64":"5WwZioT5IAYi7AfeJKsbmGBsm7GZk96vFr6jX1tqqsnNl2GM9quKoIRhFzIOk4hRq8r42bBeTZ6SE7CHwJ4GAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e8e9627ef57a98ca987649e3a4dc3c923dd21c78d1abf33c3dd50878f676c6b","last_reissued_at":"2026-07-05T03:47:33.215532Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:47:33.215532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RFLBAT: A Robust Federated Learning Algorithm against Backdoor Attack","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.CR","authors_text":"Dihua Zhai, Yongkang Wang, Yuanqing Xia, Yufeng Zhan","submitted_at":"2022-01-11T04:19:20Z","abstract_excerpt":"Federated learning (FL) is a distributed machine learning paradigm where enormous scattered clients (e.g. mobile devices or IoT devices) collaboratively train a model under the orchestration of a central server (e.g. service provider), while keeping the training data decentralized. Unfortunately, FL is susceptible to a variety of attacks, including backdoor attack, which is made substantially worse in the presence of malicious attackers. Most of algorithms usually assume that the malicious at tackers no more than benign clients or the data distribution is independent identically distribution ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.03772","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/2201.03772/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":"2201.03772","created_at":"2026-07-05T03:47:33.215589+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.03772v1","created_at":"2026-07-05T03:47:33.215589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.03772","created_at":"2026-07-05T03:47:33.215589+00:00"},{"alias_kind":"pith_short_12","alias_value":"T2HJMJ7PK6UY","created_at":"2026-07-05T03:47:33.215589+00:00"},{"alias_kind":"pith_short_16","alias_value":"T2HJMJ7PK6UYZKMH","created_at":"2026-07-05T03:47:33.215589+00:00"},{"alias_kind":"pith_short_8","alias_value":"T2HJMJ7P","created_at":"2026-07-05T03:47:33.215589+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.02115","citing_title":"Coward: Collision-based OOD Watermarking for Practical Proactive Federated Backdoor Detection","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03862","citing_title":"SecureAFL: Secure Asynchronous Federated Learning","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T2HJMJ7PK6UYZKMHMSPDUTODZE","json":"https://pith.science/pith/T2HJMJ7PK6UYZKMHMSPDUTODZE.json","graph_json":"https://pith.science/api/pith-number/T2HJMJ7PK6UYZKMHMSPDUTODZE/graph.json","events_json":"https://pith.science/api/pith-number/T2HJMJ7PK6UYZKMHMSPDUTODZE/events.json","paper":"https://pith.science/paper/T2HJMJ7P"},"agent_actions":{"view_html":"https://pith.science/pith/T2HJMJ7PK6UYZKMHMSPDUTODZE","download_json":"https://pith.science/pith/T2HJMJ7PK6UYZKMHMSPDUTODZE.json","view_paper":"https://pith.science/paper/T2HJMJ7P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.03772&json=true","fetch_graph":"https://pith.science/api/pith-number/T2HJMJ7PK6UYZKMHMSPDUTODZE/graph.json","fetch_events":"https://pith.science/api/pith-number/T2HJMJ7PK6UYZKMHMSPDUTODZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T2HJMJ7PK6UYZKMHMSPDUTODZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T2HJMJ7PK6UYZKMHMSPDUTODZE/action/storage_attestation","attest_author":"https://pith.science/pith/T2HJMJ7PK6UYZKMHMSPDUTODZE/action/author_attestation","sign_citation":"https://pith.science/pith/T2HJMJ7PK6UYZKMHMSPDUTODZE/action/citation_signature","submit_replication":"https://pith.science/pith/T2HJMJ7PK6UYZKMHMSPDUTODZE/action/replication_record"}},"created_at":"2026-07-05T03:47:33.215589+00:00","updated_at":"2026-07-05T03:47:33.215589+00:00"}