{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:S3XA3WS57FSCHDDIG5BMOLLMNQ","short_pith_number":"pith:S3XA3WS5","schema_version":"1.0","canonical_sha256":"96ee0dda5df964238c683742c72d6c6c111ec14e9476f51902b7d3652cee5352","source":{"kind":"arxiv","id":"1912.11464","version":3},"attestation_state":"computed","paper":{"title":"Attack-Resistant Federated Learning with Residual-based Reweighting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Li, Chulin Xie, Qifeng Chen, Shuhao Fu","submitted_at":"2019-12-24T18:42:00Z","abstract_excerpt":"Federated learning has a variety of applications in multiple domains by utilizing private training data stored on different devices. However, the aggregation process in federated learning is highly vulnerable to adversarial attacks so that the global model may behave abnormally under attacks. To tackle this challenge, we present a novel aggregation algorithm with residual-based reweighting to defend federated learning. Our aggregation algorithm combines repeated median regression with the reweighting scheme in iteratively reweighted least squares. Our experiments show that our aggregation algo"},"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":"1912.11464","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-24T18:42:00Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"84f2e4006e2f5099df6d4c89ffe3d3b0e38e9c12665a55fc78da521cec4d6362","abstract_canon_sha256":"c44d5278e4baadca5fe91a2857d81ea320a45dfd09e52a46f7196b63f9b896f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:05:38.360417Z","signature_b64":"Zov39pKJgr465v0+aAKBx2naTcLMDiIgQ8U93Il5aT1d0O6UkPtpVGCKMfYfsQFeJWCtbuttKDvnOTHfefsbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96ee0dda5df964238c683742c72d6c6c111ec14e9476f51902b7d3652cee5352","last_reissued_at":"2026-07-05T02:05:38.359960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:05:38.359960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attack-Resistant Federated Learning with Residual-based Reweighting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Li, Chulin Xie, Qifeng Chen, Shuhao Fu","submitted_at":"2019-12-24T18:42:00Z","abstract_excerpt":"Federated learning has a variety of applications in multiple domains by utilizing private training data stored on different devices. However, the aggregation process in federated learning is highly vulnerable to adversarial attacks so that the global model may behave abnormally under attacks. To tackle this challenge, we present a novel aggregation algorithm with residual-based reweighting to defend federated learning. Our aggregation algorithm combines repeated median regression with the reweighting scheme in iteratively reweighted least squares. Our experiments show that our aggregation algo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.11464","kind":"arxiv","version":3},"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/1912.11464/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":"1912.11464","created_at":"2026-07-05T02:05:38.360016+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.11464v3","created_at":"2026-07-05T02:05:38.360016+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.11464","created_at":"2026-07-05T02:05:38.360016+00:00"},{"alias_kind":"pith_short_12","alias_value":"S3XA3WS57FSC","created_at":"2026-07-05T02:05:38.360016+00:00"},{"alias_kind":"pith_short_16","alias_value":"S3XA3WS57FSCHDDI","created_at":"2026-07-05T02:05:38.360016+00:00"},{"alias_kind":"pith_short_8","alias_value":"S3XA3WS5","created_at":"2026-07-05T02:05:38.360016+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05211","citing_title":"Decoding FL Defenses: Systemization, Pitfalls, and Remedies","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S3XA3WS57FSCHDDIG5BMOLLMNQ","json":"https://pith.science/pith/S3XA3WS57FSCHDDIG5BMOLLMNQ.json","graph_json":"https://pith.science/api/pith-number/S3XA3WS57FSCHDDIG5BMOLLMNQ/graph.json","events_json":"https://pith.science/api/pith-number/S3XA3WS57FSCHDDIG5BMOLLMNQ/events.json","paper":"https://pith.science/paper/S3XA3WS5"},"agent_actions":{"view_html":"https://pith.science/pith/S3XA3WS57FSCHDDIG5BMOLLMNQ","download_json":"https://pith.science/pith/S3XA3WS57FSCHDDIG5BMOLLMNQ.json","view_paper":"https://pith.science/paper/S3XA3WS5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.11464&json=true","fetch_graph":"https://pith.science/api/pith-number/S3XA3WS57FSCHDDIG5BMOLLMNQ/graph.json","fetch_events":"https://pith.science/api/pith-number/S3XA3WS57FSCHDDIG5BMOLLMNQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S3XA3WS57FSCHDDIG5BMOLLMNQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S3XA3WS57FSCHDDIG5BMOLLMNQ/action/storage_attestation","attest_author":"https://pith.science/pith/S3XA3WS57FSCHDDIG5BMOLLMNQ/action/author_attestation","sign_citation":"https://pith.science/pith/S3XA3WS57FSCHDDIG5BMOLLMNQ/action/citation_signature","submit_replication":"https://pith.science/pith/S3XA3WS57FSCHDDIG5BMOLLMNQ/action/replication_record"}},"created_at":"2026-07-05T02:05:38.360016+00:00","updated_at":"2026-07-05T02:05:38.360016+00:00"}