{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SCPNUYMERUMAKNRAW7EKJUZODO","short_pith_number":"pith:SCPNUYME","schema_version":"1.0","canonical_sha256":"909eda61848d18053620b7c8a4d32e1b95ccdd8df9f1b36ca81f95c5f4033357","source":{"kind":"arxiv","id":"1812.02863","version":1},"attestation_state":"computed","paper":{"title":"Privacy Partitioning: Protecting User Data During the Deep Learning Inference Phase","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CR","authors_text":"Emmanuel Owusu, Jianfeng Chi, Patrick Tague, Tong Yu, William Chan, Xuwang Yin, Yuan Tian","submitted_at":"2018-12-07T00:42:06Z","abstract_excerpt":"We present a practical method for protecting data during the inference phase of deep learning based on bipartite topology threat modeling and an interactive adversarial deep network construction. We term this approach \\emph{Privacy Partitioning}. In the proposed framework, we split the machine learning models and deploy a few layers into users' local devices, and the rest of the layers into a remote server. We propose an approach to protect user's data during the inference phase, while still achieve good classification accuracy.\n  We conduct an experimental evaluation of this approach on bench"},"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":"1812.02863","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2018-12-07T00:42:06Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"3915b7796c2e90ac126c69b97a196e201a984a87bd637907ecf7cf8457c2d420","abstract_canon_sha256":"9ca7fb789195004dc9386827f32255ae3798c55862bfc5378274c43db6c9f08d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:51.641533Z","signature_b64":"DxP/v97zqm6JMaIKutC9GLscQLKExGKqA/PQ+Exu5AzkIDx1t3GMz+eaH4jZ0ZJ7HRIjPjCaD+hNmPP4v97ZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"909eda61848d18053620b7c8a4d32e1b95ccdd8df9f1b36ca81f95c5f4033357","last_reissued_at":"2026-05-17T23:58:51.641035Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:51.641035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Privacy Partitioning: Protecting User Data During the Deep Learning Inference Phase","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CR","authors_text":"Emmanuel Owusu, Jianfeng Chi, Patrick Tague, Tong Yu, William Chan, Xuwang Yin, Yuan Tian","submitted_at":"2018-12-07T00:42:06Z","abstract_excerpt":"We present a practical method for protecting data during the inference phase of deep learning based on bipartite topology threat modeling and an interactive adversarial deep network construction. We term this approach \\emph{Privacy Partitioning}. In the proposed framework, we split the machine learning models and deploy a few layers into users' local devices, and the rest of the layers into a remote server. We propose an approach to protect user's data during the inference phase, while still achieve good classification accuracy.\n  We conduct an experimental evaluation of this approach on bench"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02863","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":""},"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":"1812.02863","created_at":"2026-05-17T23:58:51.641099+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.02863v1","created_at":"2026-05-17T23:58:51.641099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02863","created_at":"2026-05-17T23:58:51.641099+00:00"},{"alias_kind":"pith_short_12","alias_value":"SCPNUYMERUMA","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"SCPNUYMERUMAKNRA","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"SCPNUYME","created_at":"2026-05-18T12:32:50.500415+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/SCPNUYMERUMAKNRAW7EKJUZODO","json":"https://pith.science/pith/SCPNUYMERUMAKNRAW7EKJUZODO.json","graph_json":"https://pith.science/api/pith-number/SCPNUYMERUMAKNRAW7EKJUZODO/graph.json","events_json":"https://pith.science/api/pith-number/SCPNUYMERUMAKNRAW7EKJUZODO/events.json","paper":"https://pith.science/paper/SCPNUYME"},"agent_actions":{"view_html":"https://pith.science/pith/SCPNUYMERUMAKNRAW7EKJUZODO","download_json":"https://pith.science/pith/SCPNUYMERUMAKNRAW7EKJUZODO.json","view_paper":"https://pith.science/paper/SCPNUYME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.02863&json=true","fetch_graph":"https://pith.science/api/pith-number/SCPNUYMERUMAKNRAW7EKJUZODO/graph.json","fetch_events":"https://pith.science/api/pith-number/SCPNUYMERUMAKNRAW7EKJUZODO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SCPNUYMERUMAKNRAW7EKJUZODO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SCPNUYMERUMAKNRAW7EKJUZODO/action/storage_attestation","attest_author":"https://pith.science/pith/SCPNUYMERUMAKNRAW7EKJUZODO/action/author_attestation","sign_citation":"https://pith.science/pith/SCPNUYMERUMAKNRAW7EKJUZODO/action/citation_signature","submit_replication":"https://pith.science/pith/SCPNUYMERUMAKNRAW7EKJUZODO/action/replication_record"}},"created_at":"2026-05-17T23:58:51.641099+00:00","updated_at":"2026-05-17T23:58:51.641099+00:00"}