{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7QFHPK55IB6B4QPPJLIEKXH2SS","short_pith_number":"pith:7QFHPK55","schema_version":"1.0","canonical_sha256":"fc0a77abbd407c1e41ef4ad0455cfa94bea15208b74abca1f164d2369dd9d794","source":{"kind":"arxiv","id":"2302.01584","version":2},"attestation_state":"computed","paper":{"title":"TT-TFHE: a Torus Fully Homomorphic Encryption-Friendly Neural Network Architecture","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Adrien Benamira, Sayandeep Saha, Thomas Peyrin, Tristan Gu\\'erand","submitted_at":"2023-02-03T07:32:23Z","abstract_excerpt":"This paper presents TT-TFHE, a deep neural network Fully Homomorphic Encryption (FHE) framework that effectively scales Torus FHE (TFHE) usage to tabular and image datasets using a recent family of convolutional neural networks called Truth-Table Neural Networks (TTnet). The proposed framework provides an easy-to-implement, automated TTnet-based design toolbox with an underlying (python-based) open-source Concrete implementation (CPU-based and implementing lookup tables) for inference over encrypted data. Experimental evaluation shows that TT-TFHE greatly outperforms in terms of time and accur"},"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":"2302.01584","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2023-02-03T07:32:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d23819e497a4b2eb1efe9e5d1a1dc56e46c9a7373961a2972fd3214f35e6cd35","abstract_canon_sha256":"28b9c03d8fe112d31f662ba833f5ee0bb4933edefdd1acdb9ec278926a053c8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:12.282112Z","signature_b64":"EtggdbXohEBa0lirFAYMH/adxCNkJbeLaCORe+XNyBVqqbelWjD78CeeuY4jg0j1AHjZNuUvKclAQCF0T3PnBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc0a77abbd407c1e41ef4ad0455cfa94bea15208b74abca1f164d2369dd9d794","last_reissued_at":"2026-07-05T11:33:12.281632Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:12.281632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TT-TFHE: a Torus Fully Homomorphic Encryption-Friendly Neural Network Architecture","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Adrien Benamira, Sayandeep Saha, Thomas Peyrin, Tristan Gu\\'erand","submitted_at":"2023-02-03T07:32:23Z","abstract_excerpt":"This paper presents TT-TFHE, a deep neural network Fully Homomorphic Encryption (FHE) framework that effectively scales Torus FHE (TFHE) usage to tabular and image datasets using a recent family of convolutional neural networks called Truth-Table Neural Networks (TTnet). The proposed framework provides an easy-to-implement, automated TTnet-based design toolbox with an underlying (python-based) open-source Concrete implementation (CPU-based and implementing lookup tables) for inference over encrypted data. Experimental evaluation shows that TT-TFHE greatly outperforms in terms of time and accur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01584","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2302.01584/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":"2302.01584","created_at":"2026-07-05T11:33:12.281686+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.01584v2","created_at":"2026-07-05T11:33:12.281686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01584","created_at":"2026-07-05T11:33:12.281686+00:00"},{"alias_kind":"pith_short_12","alias_value":"7QFHPK55IB6B","created_at":"2026-07-05T11:33:12.281686+00:00"},{"alias_kind":"pith_short_16","alias_value":"7QFHPK55IB6B4QPP","created_at":"2026-07-05T11:33:12.281686+00:00"},{"alias_kind":"pith_short_8","alias_value":"7QFHPK55","created_at":"2026-07-05T11:33:12.281686+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16834","citing_title":"Towards Deep Encrypted Training: Low-Latency, Memory-Efficient, and High-Throughput Inference for Privacy-Preserving Neural Networks","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7QFHPK55IB6B4QPPJLIEKXH2SS","json":"https://pith.science/pith/7QFHPK55IB6B4QPPJLIEKXH2SS.json","graph_json":"https://pith.science/api/pith-number/7QFHPK55IB6B4QPPJLIEKXH2SS/graph.json","events_json":"https://pith.science/api/pith-number/7QFHPK55IB6B4QPPJLIEKXH2SS/events.json","paper":"https://pith.science/paper/7QFHPK55"},"agent_actions":{"view_html":"https://pith.science/pith/7QFHPK55IB6B4QPPJLIEKXH2SS","download_json":"https://pith.science/pith/7QFHPK55IB6B4QPPJLIEKXH2SS.json","view_paper":"https://pith.science/paper/7QFHPK55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.01584&json=true","fetch_graph":"https://pith.science/api/pith-number/7QFHPK55IB6B4QPPJLIEKXH2SS/graph.json","fetch_events":"https://pith.science/api/pith-number/7QFHPK55IB6B4QPPJLIEKXH2SS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7QFHPK55IB6B4QPPJLIEKXH2SS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7QFHPK55IB6B4QPPJLIEKXH2SS/action/storage_attestation","attest_author":"https://pith.science/pith/7QFHPK55IB6B4QPPJLIEKXH2SS/action/author_attestation","sign_citation":"https://pith.science/pith/7QFHPK55IB6B4QPPJLIEKXH2SS/action/citation_signature","submit_replication":"https://pith.science/pith/7QFHPK55IB6B4QPPJLIEKXH2SS/action/replication_record"}},"created_at":"2026-07-05T11:33:12.281686+00:00","updated_at":"2026-07-05T11:33:12.281686+00:00"}