{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HLBFD772G4F7T6WAJOQNEMKFOW","short_pith_number":"pith:HLBFD772","schema_version":"1.0","canonical_sha256":"3ac251fffa370bf9fac04ba0d231457589a0ea7717a41ad4c295ca3a6d57cf90","source":{"kind":"arxiv","id":"1812.10659","version":2},"attestation_state":"computed","paper":{"title":"Low Latency Privacy Preserving Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alon Brutzkus, Oren Elisha, Ran Gilad-Bachrach","submitted_at":"2018-12-27T08:38:54Z","abstract_excerpt":"When applying machine learning to sensitive data, one has to find a balance between accuracy, information security, and computational-complexity. Recent studies combined Homomorphic Encryption with neural networks to make inferences while protecting against information leakage. However, these methods are limited by the width and depth of neural networks that can be used (and hence the accuracy) and exhibit high latency even for relatively simple networks. In this study we provide two solutions that address these limitations. In the first solution, we present more than $10\\times$ improvement in"},"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":"1812.10659","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-27T08:38:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d8127d87a7b779eec486a56ab21c33048abb6f509a3f9d93605c4ed314eea74b","abstract_canon_sha256":"0ab28130787ed43c1e5d6a85e60ef35240c8a2f5fae61eea10df964ac6d07e7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:02.572276Z","signature_b64":"zgZZjzObYXhLC/Bk3iGkZIZguS0GQs/KUWHHvIeN54M4rqUo/5zkSKBEmjVoc4rb20we//669Y8gbxhPHZOnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ac251fffa370bf9fac04ba0d231457589a0ea7717a41ad4c295ca3a6d57cf90","last_reissued_at":"2026-05-17T23:44:02.571871Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:02.571871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low Latency Privacy Preserving Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alon Brutzkus, Oren Elisha, Ran Gilad-Bachrach","submitted_at":"2018-12-27T08:38:54Z","abstract_excerpt":"When applying machine learning to sensitive data, one has to find a balance between accuracy, information security, and computational-complexity. Recent studies combined Homomorphic Encryption with neural networks to make inferences while protecting against information leakage. However, these methods are limited by the width and depth of neural networks that can be used (and hence the accuracy) and exhibit high latency even for relatively simple networks. In this study we provide two solutions that address these limitations. In the first solution, we present more than $10\\times$ improvement in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.10659","kind":"arxiv","version":2},"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":"1812.10659","created_at":"2026-05-17T23:44:02.571937+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.10659v2","created_at":"2026-05-17T23:44:02.571937+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.10659","created_at":"2026-05-17T23:44:02.571937+00:00"},{"alias_kind":"pith_short_12","alias_value":"HLBFD772G4F7","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"HLBFD772G4F7T6WA","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"HLBFD772","created_at":"2026-05-18T12:32:28.185984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.07047","citing_title":"Leveraging ASIC AI Chips for Homomorphic Encryption","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HLBFD772G4F7T6WAJOQNEMKFOW","json":"https://pith.science/pith/HLBFD772G4F7T6WAJOQNEMKFOW.json","graph_json":"https://pith.science/api/pith-number/HLBFD772G4F7T6WAJOQNEMKFOW/graph.json","events_json":"https://pith.science/api/pith-number/HLBFD772G4F7T6WAJOQNEMKFOW/events.json","paper":"https://pith.science/paper/HLBFD772"},"agent_actions":{"view_html":"https://pith.science/pith/HLBFD772G4F7T6WAJOQNEMKFOW","download_json":"https://pith.science/pith/HLBFD772G4F7T6WAJOQNEMKFOW.json","view_paper":"https://pith.science/paper/HLBFD772","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.10659&json=true","fetch_graph":"https://pith.science/api/pith-number/HLBFD772G4F7T6WAJOQNEMKFOW/graph.json","fetch_events":"https://pith.science/api/pith-number/HLBFD772G4F7T6WAJOQNEMKFOW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HLBFD772G4F7T6WAJOQNEMKFOW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HLBFD772G4F7T6WAJOQNEMKFOW/action/storage_attestation","attest_author":"https://pith.science/pith/HLBFD772G4F7T6WAJOQNEMKFOW/action/author_attestation","sign_citation":"https://pith.science/pith/HLBFD772G4F7T6WAJOQNEMKFOW/action/citation_signature","submit_replication":"https://pith.science/pith/HLBFD772G4F7T6WAJOQNEMKFOW/action/replication_record"}},"created_at":"2026-05-17T23:44:02.571937+00:00","updated_at":"2026-05-17T23:44:02.571937+00:00"}