{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UAVTCC6M2DFGH3PGVOQUYBA4LR","short_pith_number":"pith:UAVTCC6M","schema_version":"1.0","canonical_sha256":"a02b310bccd0ca63ede6aba14c041c5c41df1cdfcefba2a00d04ee55ef0cbedc","source":{"kind":"arxiv","id":"2303.08581","version":1},"attestation_state":"computed","paper":{"title":"Model Extraction Attacks on Split Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Adnan Siraj Rakin, Chaitali Chakrabarti, Deliang Fan, Jingtao Li, Li Yang, Xing Chen, Zhezhi He","submitted_at":"2023-03-13T20:21:51Z","abstract_excerpt":"Federated Learning (FL) is a popular collaborative learning scheme involving multiple clients and a server. FL focuses on protecting clients' data but turns out to be highly vulnerable to Intellectual Property (IP) threats. Since FL periodically collects and distributes the model parameters, a free-rider can download the latest model and thus steal model IP. Split Federated Learning (SFL), a recent variant of FL that supports training with resource-constrained clients, splits the model into two, giving one part of the model to clients (client-side model), and the remaining part to the server ("},"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":"2303.08581","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-13T20:21:51Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5bb88f6cd65a38c24f1a9d887e589e1a8e80a07ba3e45c00e6aa4a536994d2a3","abstract_canon_sha256":"cde955fd16eaf7b99b54af676a1b84fd52c863a483f6f26cb577b91e1ba38db4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:34.818178Z","signature_b64":"xHmkCdiL0o8Hr6mcbQl64GTYaXQLTbaOnzMvxbgav3c2zCoNfp9gchgP9x5ukBLmsFAR04m+qvtVxGOEPm53DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a02b310bccd0ca63ede6aba14c041c5c41df1cdfcefba2a00d04ee55ef0cbedc","last_reissued_at":"2026-07-05T05:51:34.817852Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:34.817852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model Extraction Attacks on Split Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Adnan Siraj Rakin, Chaitali Chakrabarti, Deliang Fan, Jingtao Li, Li Yang, Xing Chen, Zhezhi He","submitted_at":"2023-03-13T20:21:51Z","abstract_excerpt":"Federated Learning (FL) is a popular collaborative learning scheme involving multiple clients and a server. FL focuses on protecting clients' data but turns out to be highly vulnerable to Intellectual Property (IP) threats. Since FL periodically collects and distributes the model parameters, a free-rider can download the latest model and thus steal model IP. Split Federated Learning (SFL), a recent variant of FL that supports training with resource-constrained clients, splits the model into two, giving one part of the model to clients (client-side model), and the remaining part to the server ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08581","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/2303.08581/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":"2303.08581","created_at":"2026-07-05T05:51:34.817908+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.08581v1","created_at":"2026-07-05T05:51:34.817908+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08581","created_at":"2026-07-05T05:51:34.817908+00:00"},{"alias_kind":"pith_short_12","alias_value":"UAVTCC6M2DFG","created_at":"2026-07-05T05:51:34.817908+00:00"},{"alias_kind":"pith_short_16","alias_value":"UAVTCC6M2DFGH3PG","created_at":"2026-07-05T05:51:34.817908+00:00"},{"alias_kind":"pith_short_8","alias_value":"UAVTCC6M","created_at":"2026-07-05T05:51:34.817908+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.15031","citing_title":"A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives","ref_index":114,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UAVTCC6M2DFGH3PGVOQUYBA4LR","json":"https://pith.science/pith/UAVTCC6M2DFGH3PGVOQUYBA4LR.json","graph_json":"https://pith.science/api/pith-number/UAVTCC6M2DFGH3PGVOQUYBA4LR/graph.json","events_json":"https://pith.science/api/pith-number/UAVTCC6M2DFGH3PGVOQUYBA4LR/events.json","paper":"https://pith.science/paper/UAVTCC6M"},"agent_actions":{"view_html":"https://pith.science/pith/UAVTCC6M2DFGH3PGVOQUYBA4LR","download_json":"https://pith.science/pith/UAVTCC6M2DFGH3PGVOQUYBA4LR.json","view_paper":"https://pith.science/paper/UAVTCC6M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.08581&json=true","fetch_graph":"https://pith.science/api/pith-number/UAVTCC6M2DFGH3PGVOQUYBA4LR/graph.json","fetch_events":"https://pith.science/api/pith-number/UAVTCC6M2DFGH3PGVOQUYBA4LR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UAVTCC6M2DFGH3PGVOQUYBA4LR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UAVTCC6M2DFGH3PGVOQUYBA4LR/action/storage_attestation","attest_author":"https://pith.science/pith/UAVTCC6M2DFGH3PGVOQUYBA4LR/action/author_attestation","sign_citation":"https://pith.science/pith/UAVTCC6M2DFGH3PGVOQUYBA4LR/action/citation_signature","submit_replication":"https://pith.science/pith/UAVTCC6M2DFGH3PGVOQUYBA4LR/action/replication_record"}},"created_at":"2026-07-05T05:51:34.817908+00:00","updated_at":"2026-07-05T05:51:34.817908+00:00"}