{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5HFMW6CZJ7U5S6UJCWUDYKO6JM","short_pith_number":"pith:5HFMW6CZ","schema_version":"1.0","canonical_sha256":"e9cacb78594fe9d97a8915a83c29de4b0842034c8b8eec239fb1820d9a42467c","source":{"kind":"arxiv","id":"2502.00587","version":2},"attestation_state":"computed","paper":{"title":"Robust Knowledge Distillation in Federated Learning: Counteracting Backdoor Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Antonios Gouglidis, Ebtisaam Alharbi, Leandro Soriano Marcolino, Qiang Ni","submitted_at":"2025-02-01T22:57:08Z","abstract_excerpt":"Federated Learning (FL) enables collaborative model training across multiple devices while preserving data privacy. However, it remains susceptible to backdoor attacks, where malicious participants can compromise the global model. Existing defence methods are limited by strict assumptions on data heterogeneity (Non-Independent and Identically Distributed data) and the proportion of malicious clients, reducing their practicality and effectiveness. To overcome these limitations, we propose Robust Knowledge Distillation (RKD), a novel defence mechanism that enhances model integrity without relyin"},"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":"2502.00587","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-02-01T22:57:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"52d39d858b427b7452a4c07f5429cb0453bb851d195c1dc4d5d69603bf63d55c","abstract_canon_sha256":"9a69095cff032dd9cd1dad261e1bd57ccd4d217723ea1bb4ad5d4858d02c94ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:37.528127Z","signature_b64":"j15VuP56VTUYsYwfSPAk6HsZd345H8tUBxziqEExIF7XtedBq6RyDqaptYnZp/Ud/yKxJpv32udOlk4TqBNdDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9cacb78594fe9d97a8915a83c29de4b0842034c8b8eec239fb1820d9a42467c","last_reissued_at":"2026-07-05T10:19:37.527671Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:37.527671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Knowledge Distillation in Federated Learning: Counteracting Backdoor Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Antonios Gouglidis, Ebtisaam Alharbi, Leandro Soriano Marcolino, Qiang Ni","submitted_at":"2025-02-01T22:57:08Z","abstract_excerpt":"Federated Learning (FL) enables collaborative model training across multiple devices while preserving data privacy. However, it remains susceptible to backdoor attacks, where malicious participants can compromise the global model. Existing defence methods are limited by strict assumptions on data heterogeneity (Non-Independent and Identically Distributed data) and the proportion of malicious clients, reducing their practicality and effectiveness. To overcome these limitations, we propose Robust Knowledge Distillation (RKD), a novel defence mechanism that enhances model integrity without relyin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00587","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/2502.00587/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":"2502.00587","created_at":"2026-07-05T10:19:37.527730+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.00587v2","created_at":"2026-07-05T10:19:37.527730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00587","created_at":"2026-07-05T10:19:37.527730+00:00"},{"alias_kind":"pith_short_12","alias_value":"5HFMW6CZJ7U5","created_at":"2026-07-05T10:19:37.527730+00:00"},{"alias_kind":"pith_short_16","alias_value":"5HFMW6CZJ7U5S6UJ","created_at":"2026-07-05T10:19:37.527730+00:00"},{"alias_kind":"pith_short_8","alias_value":"5HFMW6CZ","created_at":"2026-07-05T10:19:37.527730+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.08830","citing_title":"Federated Large Language Models: Feasibility, Robustness, Security and Future Directions","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5HFMW6CZJ7U5S6UJCWUDYKO6JM","json":"https://pith.science/pith/5HFMW6CZJ7U5S6UJCWUDYKO6JM.json","graph_json":"https://pith.science/api/pith-number/5HFMW6CZJ7U5S6UJCWUDYKO6JM/graph.json","events_json":"https://pith.science/api/pith-number/5HFMW6CZJ7U5S6UJCWUDYKO6JM/events.json","paper":"https://pith.science/paper/5HFMW6CZ"},"agent_actions":{"view_html":"https://pith.science/pith/5HFMW6CZJ7U5S6UJCWUDYKO6JM","download_json":"https://pith.science/pith/5HFMW6CZJ7U5S6UJCWUDYKO6JM.json","view_paper":"https://pith.science/paper/5HFMW6CZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.00587&json=true","fetch_graph":"https://pith.science/api/pith-number/5HFMW6CZJ7U5S6UJCWUDYKO6JM/graph.json","fetch_events":"https://pith.science/api/pith-number/5HFMW6CZJ7U5S6UJCWUDYKO6JM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5HFMW6CZJ7U5S6UJCWUDYKO6JM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5HFMW6CZJ7U5S6UJCWUDYKO6JM/action/storage_attestation","attest_author":"https://pith.science/pith/5HFMW6CZJ7U5S6UJCWUDYKO6JM/action/author_attestation","sign_citation":"https://pith.science/pith/5HFMW6CZJ7U5S6UJCWUDYKO6JM/action/citation_signature","submit_replication":"https://pith.science/pith/5HFMW6CZJ7U5S6UJCWUDYKO6JM/action/replication_record"}},"created_at":"2026-07-05T10:19:37.527730+00:00","updated_at":"2026-07-05T10:19:37.527730+00:00"}