{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BWDDW4BNWKEOE7UCSEMPEKJM6A","short_pith_number":"pith:BWDDW4BN","schema_version":"1.0","canonical_sha256":"0d863b702db288e27e829118f2292cf014f4220896d2e6d097c1723c4c6e08fe","source":{"kind":"arxiv","id":"2409.08372","version":2},"attestation_state":"computed","paper":{"title":"FedProphet: Memory-Efficient Federated Adversarial Training via Robust and Consistent Cascade Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amin Hass, Aolin Ding, Hai \"Helen\" Li, Jingyang Zhang, Louis DiValentin, Minxue Tang, Yiran Chen, Yitu Wang","submitted_at":"2024-09-12T19:39:14Z","abstract_excerpt":"Federated Adversarial Training (FAT) can supplement robustness against adversarial examples to Federated Learning (FL), promoting a meaningful step toward trustworthy AI. However, FAT requires large models to preserve high accuracy while achieving strong robustness, incurring high memory-swapping latency when training on memory-constrained edge devices. Existing memory-efficient FL methods suffer from poor accuracy and weak robustness due to inconsistent local and global models. In this paper, we propose FedProphet, a novel FAT framework that can achieve memory efficiency, robustness, and cons"},"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":"2409.08372","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-12T19:39:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"947c3c535b12785abd5e22489aa8cb52e9ccfd8e86d301611ce97b3fe211c47a","abstract_canon_sha256":"19ff2a906bb358d53a9c4fc930c2a2d33038cd0756435f209dc5163e07361f6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:09.098897Z","signature_b64":"tPj7rht+yqo77v/YI2KndYDt4YLtzSpAixdIcK7s8zdY+N7YvN+ueD4EEzgPUYodh/Vblxt7d4t9o6Tb3KdYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d863b702db288e27e829118f2292cf014f4220896d2e6d097c1723c4c6e08fe","last_reissued_at":"2026-07-05T10:49:09.098392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:09.098392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedProphet: Memory-Efficient Federated Adversarial Training via Robust and Consistent Cascade Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amin Hass, Aolin Ding, Hai \"Helen\" Li, Jingyang Zhang, Louis DiValentin, Minxue Tang, Yiran Chen, Yitu Wang","submitted_at":"2024-09-12T19:39:14Z","abstract_excerpt":"Federated Adversarial Training (FAT) can supplement robustness against adversarial examples to Federated Learning (FL), promoting a meaningful step toward trustworthy AI. However, FAT requires large models to preserve high accuracy while achieving strong robustness, incurring high memory-swapping latency when training on memory-constrained edge devices. Existing memory-efficient FL methods suffer from poor accuracy and weak robustness due to inconsistent local and global models. In this paper, we propose FedProphet, a novel FAT framework that can achieve memory efficiency, robustness, and cons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08372","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/2409.08372/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":"2409.08372","created_at":"2026-07-05T10:49:09.098453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.08372v2","created_at":"2026-07-05T10:49:09.098453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08372","created_at":"2026-07-05T10:49:09.098453+00:00"},{"alias_kind":"pith_short_12","alias_value":"BWDDW4BNWKEO","created_at":"2026-07-05T10:49:09.098453+00:00"},{"alias_kind":"pith_short_16","alias_value":"BWDDW4BNWKEOE7UC","created_at":"2026-07-05T10:49:09.098453+00:00"},{"alias_kind":"pith_short_8","alias_value":"BWDDW4BN","created_at":"2026-07-05T10:49:09.098453+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/BWDDW4BNWKEOE7UCSEMPEKJM6A","json":"https://pith.science/pith/BWDDW4BNWKEOE7UCSEMPEKJM6A.json","graph_json":"https://pith.science/api/pith-number/BWDDW4BNWKEOE7UCSEMPEKJM6A/graph.json","events_json":"https://pith.science/api/pith-number/BWDDW4BNWKEOE7UCSEMPEKJM6A/events.json","paper":"https://pith.science/paper/BWDDW4BN"},"agent_actions":{"view_html":"https://pith.science/pith/BWDDW4BNWKEOE7UCSEMPEKJM6A","download_json":"https://pith.science/pith/BWDDW4BNWKEOE7UCSEMPEKJM6A.json","view_paper":"https://pith.science/paper/BWDDW4BN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.08372&json=true","fetch_graph":"https://pith.science/api/pith-number/BWDDW4BNWKEOE7UCSEMPEKJM6A/graph.json","fetch_events":"https://pith.science/api/pith-number/BWDDW4BNWKEOE7UCSEMPEKJM6A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BWDDW4BNWKEOE7UCSEMPEKJM6A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BWDDW4BNWKEOE7UCSEMPEKJM6A/action/storage_attestation","attest_author":"https://pith.science/pith/BWDDW4BNWKEOE7UCSEMPEKJM6A/action/author_attestation","sign_citation":"https://pith.science/pith/BWDDW4BNWKEOE7UCSEMPEKJM6A/action/citation_signature","submit_replication":"https://pith.science/pith/BWDDW4BNWKEOE7UCSEMPEKJM6A/action/replication_record"}},"created_at":"2026-07-05T10:49:09.098453+00:00","updated_at":"2026-07-05T10:49:09.098453+00:00"}