{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H5I2FMTWIJCZZS2LPTU4FX25WD","short_pith_number":"pith:H5I2FMTW","schema_version":"1.0","canonical_sha256":"3f51a2b27642459ccb4b7ce9c2df5db0dfe189f085799de1a5bc1e7c1019612d","source":{"kind":"arxiv","id":"2505.05872","version":1},"attestation_state":"computed","paper":{"title":"A Taxonomy of Attacks and Defenses in Split Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Alptekin K\\\"up\\c{c}\\\"u, Aqsa Shabbir, Halil \\.Ibrahim Kanpak, Sinem Sav","submitted_at":"2025-05-09T08:19:15Z","abstract_excerpt":"Split Learning (SL) has emerged as a promising paradigm for distributed deep learning, allowing resource-constrained clients to offload portions of their model computation to servers while maintaining collaborative learning. However, recent research has demonstrated that SL remains vulnerable to a range of privacy and security threats, including information leakage, model inversion, and adversarial attacks. While various defense mechanisms have been proposed, a systematic understanding of the attack landscape and corresponding countermeasures is still lacking. In this study, we present a compr"},"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":"2505.05872","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-05-09T08:19:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"61259079dab32cac215e298f58d01f156b2906d26465240d91287f6a80a350d3","abstract_canon_sha256":"8dc030ffa95f277ca6addb4e2d08653d235fce35ec8fe18efc524cafba51035b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:49.171181Z","signature_b64":"VxgCWj0MYEdxcB54/abnLJ0am0irUznN5Ib5Vfo3MR2mZ+sbJ4TxP4NhLkd69+ra3a8Kw4oxMWX1Yxih/pL8DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f51a2b27642459ccb4b7ce9c2df5db0dfe189f085799de1a5bc1e7c1019612d","last_reissued_at":"2026-07-05T11:00:49.170667Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:49.170667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Taxonomy of Attacks and Defenses in Split Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Alptekin K\\\"up\\c{c}\\\"u, Aqsa Shabbir, Halil \\.Ibrahim Kanpak, Sinem Sav","submitted_at":"2025-05-09T08:19:15Z","abstract_excerpt":"Split Learning (SL) has emerged as a promising paradigm for distributed deep learning, allowing resource-constrained clients to offload portions of their model computation to servers while maintaining collaborative learning. However, recent research has demonstrated that SL remains vulnerable to a range of privacy and security threats, including information leakage, model inversion, and adversarial attacks. While various defense mechanisms have been proposed, a systematic understanding of the attack landscape and corresponding countermeasures is still lacking. In this study, we present a compr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05872","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/2505.05872/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":"2505.05872","created_at":"2026-07-05T11:00:49.170733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.05872v1","created_at":"2026-07-05T11:00:49.170733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05872","created_at":"2026-07-05T11:00:49.170733+00:00"},{"alias_kind":"pith_short_12","alias_value":"H5I2FMTWIJCZ","created_at":"2026-07-05T11:00:49.170733+00:00"},{"alias_kind":"pith_short_16","alias_value":"H5I2FMTWIJCZZS2L","created_at":"2026-07-05T11:00:49.170733+00:00"},{"alias_kind":"pith_short_8","alias_value":"H5I2FMTW","created_at":"2026-07-05T11:00:49.170733+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24468","citing_title":"A Survey on Split Learning for LLM Fine-Tuning: Models, Systems, and Privacy Optimizations","ref_index":122,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H5I2FMTWIJCZZS2LPTU4FX25WD","json":"https://pith.science/pith/H5I2FMTWIJCZZS2LPTU4FX25WD.json","graph_json":"https://pith.science/api/pith-number/H5I2FMTWIJCZZS2LPTU4FX25WD/graph.json","events_json":"https://pith.science/api/pith-number/H5I2FMTWIJCZZS2LPTU4FX25WD/events.json","paper":"https://pith.science/paper/H5I2FMTW"},"agent_actions":{"view_html":"https://pith.science/pith/H5I2FMTWIJCZZS2LPTU4FX25WD","download_json":"https://pith.science/pith/H5I2FMTWIJCZZS2LPTU4FX25WD.json","view_paper":"https://pith.science/paper/H5I2FMTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.05872&json=true","fetch_graph":"https://pith.science/api/pith-number/H5I2FMTWIJCZZS2LPTU4FX25WD/graph.json","fetch_events":"https://pith.science/api/pith-number/H5I2FMTWIJCZZS2LPTU4FX25WD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H5I2FMTWIJCZZS2LPTU4FX25WD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H5I2FMTWIJCZZS2LPTU4FX25WD/action/storage_attestation","attest_author":"https://pith.science/pith/H5I2FMTWIJCZZS2LPTU4FX25WD/action/author_attestation","sign_citation":"https://pith.science/pith/H5I2FMTWIJCZZS2LPTU4FX25WD/action/citation_signature","submit_replication":"https://pith.science/pith/H5I2FMTWIJCZZS2LPTU4FX25WD/action/replication_record"}},"created_at":"2026-07-05T11:00:49.170733+00:00","updated_at":"2026-07-05T11:00:49.170733+00:00"}