{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NPEGXSDBSMTGL3WFX2SHITLYZV","short_pith_number":"pith:NPEGXSDB","schema_version":"1.0","canonical_sha256":"6bc86bc861932665eec5bea4744d78cd42fc52185a78354fbc7f6cb3b609b5c7","source":{"kind":"arxiv","id":"2308.15783","version":1},"attestation_state":"computed","paper":{"title":"Split Without a Leak: Reducing Privacy Leakage in Split Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Antonis Michalas, Khoa Nguyen, Tanveer Khan","submitted_at":"2023-08-30T06:28:42Z","abstract_excerpt":"The popularity of Deep Learning (DL) makes the privacy of sensitive data more imperative than ever. As a result, various privacy-preserving techniques have been implemented to preserve user data privacy in DL. Among various privacy-preserving techniques, collaborative learning techniques, such as Split Learning (SL) have been utilized to accelerate the learning and prediction process. Initially, SL was considered a promising approach to data privacy. However, subsequent research has demonstrated that SL is susceptible to many types of attacks and, therefore, it cannot serve as a privacy-preser"},"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":"2308.15783","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2023-08-30T06:28:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e0a302465240f9ff0c07cd481f2a133c203114243fd13328188aa830cfedb363","abstract_canon_sha256":"5e23ef7d95ba82f8f74396d30670e9ec1b988a4b244d2606fe31e126e8a3e9a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:13.286748Z","signature_b64":"m1TCAplCQrQiZd78Dib7ITJKWwGNHty7bBvgB4xzPbwcNm4SESWvkwqUbwuqRqU+JeknPV5o9FlbV3ozpFfEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bc86bc861932665eec5bea4744d78cd42fc52185a78354fbc7f6cb3b609b5c7","last_reissued_at":"2026-07-05T06:46:13.286311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:13.286311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Split Without a Leak: Reducing Privacy Leakage in Split Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Antonis Michalas, Khoa Nguyen, Tanveer Khan","submitted_at":"2023-08-30T06:28:42Z","abstract_excerpt":"The popularity of Deep Learning (DL) makes the privacy of sensitive data more imperative than ever. As a result, various privacy-preserving techniques have been implemented to preserve user data privacy in DL. Among various privacy-preserving techniques, collaborative learning techniques, such as Split Learning (SL) have been utilized to accelerate the learning and prediction process. Initially, SL was considered a promising approach to data privacy. However, subsequent research has demonstrated that SL is susceptible to many types of attacks and, therefore, it cannot serve as a privacy-preser"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15783","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/2308.15783/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":"2308.15783","created_at":"2026-07-05T06:46:13.286380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.15783v1","created_at":"2026-07-05T06:46:13.286380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15783","created_at":"2026-07-05T06:46:13.286380+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPEGXSDBSMTG","created_at":"2026-07-05T06:46:13.286380+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPEGXSDBSMTGL3WF","created_at":"2026-07-05T06:46:13.286380+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPEGXSDB","created_at":"2026-07-05T06:46:13.286380+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/NPEGXSDBSMTGL3WFX2SHITLYZV","json":"https://pith.science/pith/NPEGXSDBSMTGL3WFX2SHITLYZV.json","graph_json":"https://pith.science/api/pith-number/NPEGXSDBSMTGL3WFX2SHITLYZV/graph.json","events_json":"https://pith.science/api/pith-number/NPEGXSDBSMTGL3WFX2SHITLYZV/events.json","paper":"https://pith.science/paper/NPEGXSDB"},"agent_actions":{"view_html":"https://pith.science/pith/NPEGXSDBSMTGL3WFX2SHITLYZV","download_json":"https://pith.science/pith/NPEGXSDBSMTGL3WFX2SHITLYZV.json","view_paper":"https://pith.science/paper/NPEGXSDB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.15783&json=true","fetch_graph":"https://pith.science/api/pith-number/NPEGXSDBSMTGL3WFX2SHITLYZV/graph.json","fetch_events":"https://pith.science/api/pith-number/NPEGXSDBSMTGL3WFX2SHITLYZV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPEGXSDBSMTGL3WFX2SHITLYZV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPEGXSDBSMTGL3WFX2SHITLYZV/action/storage_attestation","attest_author":"https://pith.science/pith/NPEGXSDBSMTGL3WFX2SHITLYZV/action/author_attestation","sign_citation":"https://pith.science/pith/NPEGXSDBSMTGL3WFX2SHITLYZV/action/citation_signature","submit_replication":"https://pith.science/pith/NPEGXSDBSMTGL3WFX2SHITLYZV/action/replication_record"}},"created_at":"2026-07-05T06:46:13.286380+00:00","updated_at":"2026-07-05T06:46:13.286380+00:00"}