{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:OOW2FVLJPQYI4TTEWOLL4J7LEM","short_pith_number":"pith:OOW2FVLJ","schema_version":"1.0","canonical_sha256":"73ada2d5697c308e4e64b396be27eb232840fa2ceaeeae4fafecd5f35e4ee636","source":{"kind":"arxiv","id":"2012.13552","version":1},"attestation_state":"computed","paper":{"title":"Neural Network Training With Homomorphic Encryption","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Kentaro Mihara, Miguel Mitsuishi, Ryohei Yamaguchi, Yusuke Maruyama","submitted_at":"2020-12-25T10:03:31Z","abstract_excerpt":"We introduce a novel method and implementation architecture to train neural networks which preserves the confidentiality of both the model and the data. Our method relies on homomorphic capability of lattice based encryption scheme. Our procedure is optimized for operations on packed ciphertexts in order to achieve efficient updates of the model parameters. Our method achieves a significant reduction of computations due to our way to perform multiplications and rotations on packed ciphertexts from a feedforward network to a back-propagation network. To verify the accuracy of the training model"},"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":"2012.13552","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2020-12-25T10:03:31Z","cross_cats_sorted":[],"title_canon_sha256":"6450280689b34e29c76ada71f897a82e5b153b3f19c4fefdf2d08aba76c6ac41","abstract_canon_sha256":"6938249b751833518aafe5ba71aac041d6bce2e0f22c326f62bd3956c45ee990"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:02:10.721621Z","signature_b64":"O36UI2IWkb2VfsUwh0Tu1pZqKG5Ne7Ivwcrmh5/cJ9Apr6uPyc3nTuRqMI7035HpWeRYe4L1p6Cn5jrLBfbKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73ada2d5697c308e4e64b396be27eb232840fa2ceaeeae4fafecd5f35e4ee636","last_reissued_at":"2026-07-05T02:02:10.721277Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:02:10.721277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Network Training With Homomorphic Encryption","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Kentaro Mihara, Miguel Mitsuishi, Ryohei Yamaguchi, Yusuke Maruyama","submitted_at":"2020-12-25T10:03:31Z","abstract_excerpt":"We introduce a novel method and implementation architecture to train neural networks which preserves the confidentiality of both the model and the data. Our method relies on homomorphic capability of lattice based encryption scheme. Our procedure is optimized for operations on packed ciphertexts in order to achieve efficient updates of the model parameters. Our method achieves a significant reduction of computations due to our way to perform multiplications and rotations on packed ciphertexts from a feedforward network to a back-propagation network. To verify the accuracy of the training model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.13552","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/2012.13552/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":"2012.13552","created_at":"2026-07-05T02:02:10.721339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.13552v1","created_at":"2026-07-05T02:02:10.721339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.13552","created_at":"2026-07-05T02:02:10.721339+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOW2FVLJPQYI","created_at":"2026-07-05T02:02:10.721339+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOW2FVLJPQYI4TTE","created_at":"2026-07-05T02:02:10.721339+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOW2FVLJ","created_at":"2026-07-05T02:02:10.721339+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.19693","citing_title":"ReBoot: Encrypted Training of Deep Neural Networks with CKKS Bootstrapping","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OOW2FVLJPQYI4TTEWOLL4J7LEM","json":"https://pith.science/pith/OOW2FVLJPQYI4TTEWOLL4J7LEM.json","graph_json":"https://pith.science/api/pith-number/OOW2FVLJPQYI4TTEWOLL4J7LEM/graph.json","events_json":"https://pith.science/api/pith-number/OOW2FVLJPQYI4TTEWOLL4J7LEM/events.json","paper":"https://pith.science/paper/OOW2FVLJ"},"agent_actions":{"view_html":"https://pith.science/pith/OOW2FVLJPQYI4TTEWOLL4J7LEM","download_json":"https://pith.science/pith/OOW2FVLJPQYI4TTEWOLL4J7LEM.json","view_paper":"https://pith.science/paper/OOW2FVLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.13552&json=true","fetch_graph":"https://pith.science/api/pith-number/OOW2FVLJPQYI4TTEWOLL4J7LEM/graph.json","fetch_events":"https://pith.science/api/pith-number/OOW2FVLJPQYI4TTEWOLL4J7LEM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOW2FVLJPQYI4TTEWOLL4J7LEM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOW2FVLJPQYI4TTEWOLL4J7LEM/action/storage_attestation","attest_author":"https://pith.science/pith/OOW2FVLJPQYI4TTEWOLL4J7LEM/action/author_attestation","sign_citation":"https://pith.science/pith/OOW2FVLJPQYI4TTEWOLL4J7LEM/action/citation_signature","submit_replication":"https://pith.science/pith/OOW2FVLJPQYI4TTEWOLL4J7LEM/action/replication_record"}},"created_at":"2026-07-05T02:02:10.721339+00:00","updated_at":"2026-07-05T02:02:10.721339+00:00"}