{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:Y6UVABLJEZCZTT2IYFFUHBO3JB","short_pith_number":"pith:Y6UVABLJ","schema_version":"1.0","canonical_sha256":"c7a9500569264599cf48c14b4385db4847bdccccc3ced113a9346c3a6dedb49e","source":{"kind":"arxiv","id":"1905.10214","version":5},"attestation_state":"computed","paper":{"title":"Partially Encrypted Machine Learning using Functional Encryption","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Pointcheval, Edouard Dufour-Sans, Francis Bach, Romain Gay, Theo Ryffel","submitted_at":"2019-05-24T13:06:53Z","abstract_excerpt":"Machine learning on encrypted data has received a lot of attention thanks to recent breakthroughs in homomorphic encryption and secure multi-party computation. It allows outsourcing computation to untrusted servers without sacrificing privacy of sensitive data. We propose a practical framework to perform partially encrypted and privacy-preserving predictions which combines adversarial training and functional encryption. We first present a new functional encryption scheme to efficiently compute quadratic functions so that the data owner controls what can be computed but is not involved in the c"},"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":"1905.10214","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T13:06:53Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"42a077d8cb801c8686d99e9b02b7a81703cd31f39c7545b29ffe0b8375280022","abstract_canon_sha256":"587ed3cff85c7295ad7a59c8f9f265faf02dc344686ccc9a683460367fa85e6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:16:48.519818Z","signature_b64":"HnjXBikTuP45Hs4eZkTQOGAmRAJV7+nfTd7OOYM5UVuKuh5EmlYVyr2VMOIdazYLKpD9oafd5Rw4/UutmPnBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7a9500569264599cf48c14b4385db4847bdccccc3ced113a9346c3a6dedb49e","last_reissued_at":"2026-07-05T03:16:48.519426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:16:48.519426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Partially Encrypted Machine Learning using Functional Encryption","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Pointcheval, Edouard Dufour-Sans, Francis Bach, Romain Gay, Theo Ryffel","submitted_at":"2019-05-24T13:06:53Z","abstract_excerpt":"Machine learning on encrypted data has received a lot of attention thanks to recent breakthroughs in homomorphic encryption and secure multi-party computation. It allows outsourcing computation to untrusted servers without sacrificing privacy of sensitive data. We propose a practical framework to perform partially encrypted and privacy-preserving predictions which combines adversarial training and functional encryption. We first present a new functional encryption scheme to efficiently compute quadratic functions so that the data owner controls what can be computed but is not involved in the c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10214","kind":"arxiv","version":5},"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/1905.10214/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":"1905.10214","created_at":"2026-07-05T03:16:48.519480+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.10214v5","created_at":"2026-07-05T03:16:48.519480+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10214","created_at":"2026-07-05T03:16:48.519480+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y6UVABLJEZCZ","created_at":"2026-07-05T03:16:48.519480+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y6UVABLJEZCZTT2I","created_at":"2026-07-05T03:16:48.519480+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y6UVABLJ","created_at":"2026-07-05T03:16:48.519480+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/Y6UVABLJEZCZTT2IYFFUHBO3JB","json":"https://pith.science/pith/Y6UVABLJEZCZTT2IYFFUHBO3JB.json","graph_json":"https://pith.science/api/pith-number/Y6UVABLJEZCZTT2IYFFUHBO3JB/graph.json","events_json":"https://pith.science/api/pith-number/Y6UVABLJEZCZTT2IYFFUHBO3JB/events.json","paper":"https://pith.science/paper/Y6UVABLJ"},"agent_actions":{"view_html":"https://pith.science/pith/Y6UVABLJEZCZTT2IYFFUHBO3JB","download_json":"https://pith.science/pith/Y6UVABLJEZCZTT2IYFFUHBO3JB.json","view_paper":"https://pith.science/paper/Y6UVABLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.10214&json=true","fetch_graph":"https://pith.science/api/pith-number/Y6UVABLJEZCZTT2IYFFUHBO3JB/graph.json","fetch_events":"https://pith.science/api/pith-number/Y6UVABLJEZCZTT2IYFFUHBO3JB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y6UVABLJEZCZTT2IYFFUHBO3JB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y6UVABLJEZCZTT2IYFFUHBO3JB/action/storage_attestation","attest_author":"https://pith.science/pith/Y6UVABLJEZCZTT2IYFFUHBO3JB/action/author_attestation","sign_citation":"https://pith.science/pith/Y6UVABLJEZCZTT2IYFFUHBO3JB/action/citation_signature","submit_replication":"https://pith.science/pith/Y6UVABLJEZCZTT2IYFFUHBO3JB/action/replication_record"}},"created_at":"2026-07-05T03:16:48.519480+00:00","updated_at":"2026-07-05T03:16:48.519480+00:00"}