{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:B3IXKVRE5WQTTYFCW7OKQUPZWP","short_pith_number":"pith:B3IXKVRE","schema_version":"1.0","canonical_sha256":"0ed1755624eda139e0a2b7dca851f9b3fdf1a886d759344c303eb9f7e71a0ac3","source":{"kind":"arxiv","id":"2309.08697","version":1},"attestation_state":"computed","paper":{"title":"A More Secure Split: Enhancing the Security of Privacy-Preserving Split Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Antonis Michalas, Khoa Nguyen, Tanveer Khan","submitted_at":"2023-09-15T18:39:30Z","abstract_excerpt":"Split learning (SL) is a new collaborative learning technique that allows participants, e.g. a client and a server, to train machine learning models without the client sharing raw data. In this setting, the client initially applies its part of the machine learning model on the raw data to generate Activation Maps (AMs) and then sends them to the server to continue the training process. Previous works in the field demonstrated that reconstructing AMs could result in privacy leakage of client data. In addition to that, existing mitigation techniques that overcome the privacy leakage of SL prove "},"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":"2309.08697","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2023-09-15T18:39:30Z","cross_cats_sorted":[],"title_canon_sha256":"94f6f81a7033138fc24308107f9c199d3c02b70d78414706262c8b0155ba89b6","abstract_canon_sha256":"e9d1e9bf167dc846701040845b2916d723c6876946d2d62b514f2de988ffe522"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:11.970433Z","signature_b64":"Fgs2+94KRJOs7ACj6JT2eIrS1O3hzy0aoU7ig2fq8natS+Ekhy5wC0c0VDcwhD9gU3WPvSzGajzxsZehnjREAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ed1755624eda139e0a2b7dca851f9b3fdf1a886d759344c303eb9f7e71a0ac3","last_reissued_at":"2026-07-05T06:51:11.969950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:11.969950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A More Secure Split: Enhancing the Security of Privacy-Preserving Split Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Antonis Michalas, Khoa Nguyen, Tanveer Khan","submitted_at":"2023-09-15T18:39:30Z","abstract_excerpt":"Split learning (SL) is a new collaborative learning technique that allows participants, e.g. a client and a server, to train machine learning models without the client sharing raw data. In this setting, the client initially applies its part of the machine learning model on the raw data to generate Activation Maps (AMs) and then sends them to the server to continue the training process. Previous works in the field demonstrated that reconstructing AMs could result in privacy leakage of client data. In addition to that, existing mitigation techniques that overcome the privacy leakage of SL prove "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08697","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/2309.08697/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":"2309.08697","created_at":"2026-07-05T06:51:11.970003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.08697v1","created_at":"2026-07-05T06:51:11.970003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08697","created_at":"2026-07-05T06:51:11.970003+00:00"},{"alias_kind":"pith_short_12","alias_value":"B3IXKVRE5WQT","created_at":"2026-07-05T06:51:11.970003+00:00"},{"alias_kind":"pith_short_16","alias_value":"B3IXKVRE5WQTTYFC","created_at":"2026-07-05T06:51:11.970003+00:00"},{"alias_kind":"pith_short_8","alias_value":"B3IXKVRE","created_at":"2026-07-05T06:51:11.970003+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/B3IXKVRE5WQTTYFCW7OKQUPZWP","json":"https://pith.science/pith/B3IXKVRE5WQTTYFCW7OKQUPZWP.json","graph_json":"https://pith.science/api/pith-number/B3IXKVRE5WQTTYFCW7OKQUPZWP/graph.json","events_json":"https://pith.science/api/pith-number/B3IXKVRE5WQTTYFCW7OKQUPZWP/events.json","paper":"https://pith.science/paper/B3IXKVRE"},"agent_actions":{"view_html":"https://pith.science/pith/B3IXKVRE5WQTTYFCW7OKQUPZWP","download_json":"https://pith.science/pith/B3IXKVRE5WQTTYFCW7OKQUPZWP.json","view_paper":"https://pith.science/paper/B3IXKVRE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.08697&json=true","fetch_graph":"https://pith.science/api/pith-number/B3IXKVRE5WQTTYFCW7OKQUPZWP/graph.json","fetch_events":"https://pith.science/api/pith-number/B3IXKVRE5WQTTYFCW7OKQUPZWP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B3IXKVRE5WQTTYFCW7OKQUPZWP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B3IXKVRE5WQTTYFCW7OKQUPZWP/action/storage_attestation","attest_author":"https://pith.science/pith/B3IXKVRE5WQTTYFCW7OKQUPZWP/action/author_attestation","sign_citation":"https://pith.science/pith/B3IXKVRE5WQTTYFCW7OKQUPZWP/action/citation_signature","submit_replication":"https://pith.science/pith/B3IXKVRE5WQTTYFCW7OKQUPZWP/action/replication_record"}},"created_at":"2026-07-05T06:51:11.970003+00:00","updated_at":"2026-07-05T06:51:11.970003+00:00"}