{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K2YBHJGIKIYOUYDHSGLQSIMEXI","short_pith_number":"pith:K2YBHJGI","schema_version":"1.0","canonical_sha256":"56b013a4c85230ea60679197092184ba1b86ce1185ca45d7a726064da926fdf1","source":{"kind":"arxiv","id":"2404.12778","version":1},"attestation_state":"computed","paper":{"title":"Defending against Data Poisoning Attacks in Federated Learning via User Elimination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Nick Galanis","submitted_at":"2024-04-19T10:36:00Z","abstract_excerpt":"In the evolving landscape of Federated Learning (FL), a new type of attacks concerns the research community, namely Data Poisoning Attacks, which threaten the model integrity by maliciously altering training data. This paper introduces a novel defensive framework focused on the strategic elimination of adversarial users within a federated model. We detect those anomalies in the aggregation phase of the Federated Algorithm, by integrating metadata gathered by the local training instances with Differential Privacy techniques, to ensure that no data leakage is possible. To our knowledge, this is "},"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":"2404.12778","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-04-19T10:36:00Z","cross_cats_sorted":[],"title_canon_sha256":"66f1952d61362cd0800a27bf227f08eecc530ffd1c5fe9a1edcf63404a7cb3c6","abstract_canon_sha256":"6e1c808a4068740a3e4c548d434bd04f3b8c590b87d7e97c2884f0f18b534ebe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:58.899118Z","signature_b64":"m/YFs9E+1s75k59OkUsTXu4+4R8AeuzvRGMxZG4cADMqGLlTpx0oNaSDwc7/rhJYeqx0kVNw8ynQq4Q9n81BBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56b013a4c85230ea60679197092184ba1b86ce1185ca45d7a726064da926fdf1","last_reissued_at":"2026-07-05T08:09:58.898573Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:58.898573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Defending against Data Poisoning Attacks in Federated Learning via User Elimination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Nick Galanis","submitted_at":"2024-04-19T10:36:00Z","abstract_excerpt":"In the evolving landscape of Federated Learning (FL), a new type of attacks concerns the research community, namely Data Poisoning Attacks, which threaten the model integrity by maliciously altering training data. This paper introduces a novel defensive framework focused on the strategic elimination of adversarial users within a federated model. We detect those anomalies in the aggregation phase of the Federated Algorithm, by integrating metadata gathered by the local training instances with Differential Privacy techniques, to ensure that no data leakage is possible. To our knowledge, this is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12778","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/2404.12778/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":"2404.12778","created_at":"2026-07-05T08:09:58.898630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.12778v1","created_at":"2026-07-05T08:09:58.898630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12778","created_at":"2026-07-05T08:09:58.898630+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2YBHJGIKIYO","created_at":"2026-07-05T08:09:58.898630+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2YBHJGIKIYOUYDH","created_at":"2026-07-05T08:09:58.898630+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2YBHJGI","created_at":"2026-07-05T08:09:58.898630+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.01186","citing_title":"Secure Cluster-Based Hierarchical Federated Learning in Vehicular Networks","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K2YBHJGIKIYOUYDHSGLQSIMEXI","json":"https://pith.science/pith/K2YBHJGIKIYOUYDHSGLQSIMEXI.json","graph_json":"https://pith.science/api/pith-number/K2YBHJGIKIYOUYDHSGLQSIMEXI/graph.json","events_json":"https://pith.science/api/pith-number/K2YBHJGIKIYOUYDHSGLQSIMEXI/events.json","paper":"https://pith.science/paper/K2YBHJGI"},"agent_actions":{"view_html":"https://pith.science/pith/K2YBHJGIKIYOUYDHSGLQSIMEXI","download_json":"https://pith.science/pith/K2YBHJGIKIYOUYDHSGLQSIMEXI.json","view_paper":"https://pith.science/paper/K2YBHJGI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.12778&json=true","fetch_graph":"https://pith.science/api/pith-number/K2YBHJGIKIYOUYDHSGLQSIMEXI/graph.json","fetch_events":"https://pith.science/api/pith-number/K2YBHJGIKIYOUYDHSGLQSIMEXI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2YBHJGIKIYOUYDHSGLQSIMEXI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2YBHJGIKIYOUYDHSGLQSIMEXI/action/storage_attestation","attest_author":"https://pith.science/pith/K2YBHJGIKIYOUYDHSGLQSIMEXI/action/author_attestation","sign_citation":"https://pith.science/pith/K2YBHJGIKIYOUYDHSGLQSIMEXI/action/citation_signature","submit_replication":"https://pith.science/pith/K2YBHJGIKIYOUYDHSGLQSIMEXI/action/replication_record"}},"created_at":"2026-07-05T08:09:58.898630+00:00","updated_at":"2026-07-05T08:09:58.898630+00:00"}