{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BSFMP3BKNHARYSVC7PIVAW7J32","short_pith_number":"pith:BSFMP3BK","schema_version":"1.0","canonical_sha256":"0c8ac7ec2a69c11c4aa2fbd1505be9de9ffdd5d2e51480bd09f788b9401c08a4","source":{"kind":"arxiv","id":"2402.12265","version":3},"attestation_state":"computed","paper":{"title":"On the Byzantine-Resilience of Distillation-Based Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Christophe Roux, Max Zimmer, Sebastian Pokutta","submitted_at":"2024-02-19T16:26:40Z","abstract_excerpt":"Federated Learning (FL) algorithms using Knowledge Distillation (KD) have received increasing attention due to their favorable properties with respect to privacy, non-i.i.d. data and communication cost. These methods depart from transmitting model parameters and instead communicate information about a learning task by sharing predictions on a public dataset. In this work, we study the performance of such approaches in the byzantine setting, where a subset of the clients act in an adversarial manner aiming to disrupt the learning process. We show that KD-based FL algorithms are remarkably resil"},"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":"2402.12265","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T16:26:40Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"5a1d25e5f5a070bde6e699be653b2616994e56b940af2d228b5268c2c77b8b2b","abstract_canon_sha256":"b3d6c0dafe3d81e08b94df7f5a70a530c23303a851554d9177b595c6f1404433"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:25.375442Z","signature_b64":"bQM/HOfaBdM9m38QD558qEzFEi5SG+Zb9rxirUt1jGJ7K6NhH3wWNHajBVh4ZXK6FtR5pRMPn7wSNlsTxKHoAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c8ac7ec2a69c11c4aa2fbd1505be9de9ffdd5d2e51480bd09f788b9401c08a4","last_reissued_at":"2026-07-05T10:32:25.374502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:25.374502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Byzantine-Resilience of Distillation-Based Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Christophe Roux, Max Zimmer, Sebastian Pokutta","submitted_at":"2024-02-19T16:26:40Z","abstract_excerpt":"Federated Learning (FL) algorithms using Knowledge Distillation (KD) have received increasing attention due to their favorable properties with respect to privacy, non-i.i.d. data and communication cost. These methods depart from transmitting model parameters and instead communicate information about a learning task by sharing predictions on a public dataset. In this work, we study the performance of such approaches in the byzantine setting, where a subset of the clients act in an adversarial manner aiming to disrupt the learning process. We show that KD-based FL algorithms are remarkably resil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12265","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/2402.12265/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":"2402.12265","created_at":"2026-07-05T10:32:25.374633+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.12265v3","created_at":"2026-07-05T10:32:25.374633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12265","created_at":"2026-07-05T10:32:25.374633+00:00"},{"alias_kind":"pith_short_12","alias_value":"BSFMP3BKNHAR","created_at":"2026-07-05T10:32:25.374633+00:00"},{"alias_kind":"pith_short_16","alias_value":"BSFMP3BKNHARYSVC","created_at":"2026-07-05T10:32:25.374633+00:00"},{"alias_kind":"pith_short_8","alias_value":"BSFMP3BK","created_at":"2026-07-05T10:32:25.374633+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/BSFMP3BKNHARYSVC7PIVAW7J32","json":"https://pith.science/pith/BSFMP3BKNHARYSVC7PIVAW7J32.json","graph_json":"https://pith.science/api/pith-number/BSFMP3BKNHARYSVC7PIVAW7J32/graph.json","events_json":"https://pith.science/api/pith-number/BSFMP3BKNHARYSVC7PIVAW7J32/events.json","paper":"https://pith.science/paper/BSFMP3BK"},"agent_actions":{"view_html":"https://pith.science/pith/BSFMP3BKNHARYSVC7PIVAW7J32","download_json":"https://pith.science/pith/BSFMP3BKNHARYSVC7PIVAW7J32.json","view_paper":"https://pith.science/paper/BSFMP3BK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.12265&json=true","fetch_graph":"https://pith.science/api/pith-number/BSFMP3BKNHARYSVC7PIVAW7J32/graph.json","fetch_events":"https://pith.science/api/pith-number/BSFMP3BKNHARYSVC7PIVAW7J32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BSFMP3BKNHARYSVC7PIVAW7J32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BSFMP3BKNHARYSVC7PIVAW7J32/action/storage_attestation","attest_author":"https://pith.science/pith/BSFMP3BKNHARYSVC7PIVAW7J32/action/author_attestation","sign_citation":"https://pith.science/pith/BSFMP3BKNHARYSVC7PIVAW7J32/action/citation_signature","submit_replication":"https://pith.science/pith/BSFMP3BKNHARYSVC7PIVAW7J32/action/replication_record"}},"created_at":"2026-07-05T10:32:25.374633+00:00","updated_at":"2026-07-05T10:32:25.374633+00:00"}