{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:X3YPVWX2QHZFOWITJ2VGG2JSTU","short_pith_number":"pith:X3YPVWX2","schema_version":"1.0","canonical_sha256":"bef0fadafa81f25759134eaa6369329d1f510a9560ca4f7cb16988622634c4ee","source":{"kind":"arxiv","id":"1902.01870","version":1},"attestation_state":"computed","paper":{"title":"Stabilizing Inputs to Approximated Nonlinear Functions for Inference with Homomorphic Encryption in Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Matthias Ossadnik, Moustafa AboulAtta, Seyed-Ahmad Ahmadi","submitted_at":"2019-02-05T19:07:07Z","abstract_excerpt":"Leveled Homomorphic Encryption (LHE) offers a potential solution that could allow sectors with sensitive data to utilize the cloud and securely deploy their models for remote inference with Deep Neural Networks (DNN). However, this application faces several obstacles due to the limitations of LHE. One of the main problems is the incompatibility of commonly used nonlinear functions in DNN with the operations supported by LHE, i.e. addition and multiplication. As common in LHE approaches, we train a model with a nonlinear function, and replace it with a low-degree polynomial approximation at inf"},"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":"1902.01870","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-05T19:07:07Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"44ee510bf86e2c4e4bb14815b80a07dcdf0096b9f7db0996b2f5f20c0085bc1e","abstract_canon_sha256":"2db1da71b6ecd39857e5440d6d71181d40b40de273b4ce66fc398ec8a44e4c7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:38.575101Z","signature_b64":"YTMhT59gxViXFfdCaH4aBPRakCWgb1sJ9rWHUSYwiPN/C6kGOpZG9pye3CsvI9vfvtd4/XHafGY/32h7QXsQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bef0fadafa81f25759134eaa6369329d1f510a9560ca4f7cb16988622634c4ee","last_reissued_at":"2026-05-17T23:54:38.574469Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:38.574469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stabilizing Inputs to Approximated Nonlinear Functions for Inference with Homomorphic Encryption in Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Matthias Ossadnik, Moustafa AboulAtta, Seyed-Ahmad Ahmadi","submitted_at":"2019-02-05T19:07:07Z","abstract_excerpt":"Leveled Homomorphic Encryption (LHE) offers a potential solution that could allow sectors with sensitive data to utilize the cloud and securely deploy their models for remote inference with Deep Neural Networks (DNN). However, this application faces several obstacles due to the limitations of LHE. One of the main problems is the incompatibility of commonly used nonlinear functions in DNN with the operations supported by LHE, i.e. addition and multiplication. As common in LHE approaches, we train a model with a nonlinear function, and replace it with a low-degree polynomial approximation at inf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.01870","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":"1902.01870","created_at":"2026-05-17T23:54:38.574576+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.01870v1","created_at":"2026-05-17T23:54:38.574576+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.01870","created_at":"2026-05-17T23:54:38.574576+00:00"},{"alias_kind":"pith_short_12","alias_value":"X3YPVWX2QHZF","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"X3YPVWX2QHZFOWIT","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"X3YPVWX2","created_at":"2026-05-18T12:33:33.725879+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/X3YPVWX2QHZFOWITJ2VGG2JSTU","json":"https://pith.science/pith/X3YPVWX2QHZFOWITJ2VGG2JSTU.json","graph_json":"https://pith.science/api/pith-number/X3YPVWX2QHZFOWITJ2VGG2JSTU/graph.json","events_json":"https://pith.science/api/pith-number/X3YPVWX2QHZFOWITJ2VGG2JSTU/events.json","paper":"https://pith.science/paper/X3YPVWX2"},"agent_actions":{"view_html":"https://pith.science/pith/X3YPVWX2QHZFOWITJ2VGG2JSTU","download_json":"https://pith.science/pith/X3YPVWX2QHZFOWITJ2VGG2JSTU.json","view_paper":"https://pith.science/paper/X3YPVWX2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.01870&json=true","fetch_graph":"https://pith.science/api/pith-number/X3YPVWX2QHZFOWITJ2VGG2JSTU/graph.json","fetch_events":"https://pith.science/api/pith-number/X3YPVWX2QHZFOWITJ2VGG2JSTU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X3YPVWX2QHZFOWITJ2VGG2JSTU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X3YPVWX2QHZFOWITJ2VGG2JSTU/action/storage_attestation","attest_author":"https://pith.science/pith/X3YPVWX2QHZFOWITJ2VGG2JSTU/action/author_attestation","sign_citation":"https://pith.science/pith/X3YPVWX2QHZFOWITJ2VGG2JSTU/action/citation_signature","submit_replication":"https://pith.science/pith/X3YPVWX2QHZFOWITJ2VGG2JSTU/action/replication_record"}},"created_at":"2026-05-17T23:54:38.574576+00:00","updated_at":"2026-05-17T23:54:38.574576+00:00"}