{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TSBP3DVG4T3OWEMN3OGXNFDWKB","short_pith_number":"pith:TSBP3DVG","schema_version":"1.0","canonical_sha256":"9c82fd8ea6e4f6eb118ddb8d76947650512a71eaf4ede09f111737f44db9bad5","source":{"kind":"arxiv","id":"2104.03152","version":2},"attestation_state":"computed","paper":{"title":"TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Alaa Eddine Belfedhal, Ayoub Benaissa, Bilal Retiat, Bogdan Cebere","submitted_at":"2021-04-07T14:32:38Z","abstract_excerpt":"Machine learning algorithms have achieved remarkable results and are widely applied in a variety of domains. These algorithms often rely on sensitive and private data such as medical and financial records. Therefore, it is vital to draw further attention regarding privacy threats and corresponding defensive techniques applied to machine learning models. In this paper, we present TenSEAL, an open-source library for Privacy-Preserving Machine Learning using Homomorphic Encryption that can be easily integrated within popular machine learning frameworks. We benchmark our implementation using MNIST"},"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":"2104.03152","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2021-04-07T14:32:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"20bfd9929d0bb168e2ab05861de0d7fa6f004776d594870338b63a73c1ef314a","abstract_canon_sha256":"7f122dbd51cc9352cfa16c131c573f48b433074b1daaaf1f02782aad0dc05eae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:35:53.927251Z","signature_b64":"dr5Sx8noT+q8ZR8C7qUtjKOpdNdKHiTGbmb3LRvsOXTDH0p/cVLnmO6+W5Thso5tCvo04mYHpG7e1zEFedeoAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c82fd8ea6e4f6eb118ddb8d76947650512a71eaf4ede09f111737f44db9bad5","last_reissued_at":"2026-07-05T02:35:53.926772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:35:53.926772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Alaa Eddine Belfedhal, Ayoub Benaissa, Bilal Retiat, Bogdan Cebere","submitted_at":"2021-04-07T14:32:38Z","abstract_excerpt":"Machine learning algorithms have achieved remarkable results and are widely applied in a variety of domains. These algorithms often rely on sensitive and private data such as medical and financial records. Therefore, it is vital to draw further attention regarding privacy threats and corresponding defensive techniques applied to machine learning models. In this paper, we present TenSEAL, an open-source library for Privacy-Preserving Machine Learning using Homomorphic Encryption that can be easily integrated within popular machine learning frameworks. We benchmark our implementation using MNIST"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.03152","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/2104.03152/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":"2104.03152","created_at":"2026-07-05T02:35:53.926828+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.03152v2","created_at":"2026-07-05T02:35:53.926828+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.03152","created_at":"2026-07-05T02:35:53.926828+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSBP3DVG4T3O","created_at":"2026-07-05T02:35:53.926828+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSBP3DVG4T3OWEMN","created_at":"2026-07-05T02:35:53.926828+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSBP3DVG","created_at":"2026-07-05T02:35:53.926828+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08521","citing_title":"Exploring CKKS Parameter Trade-offs for Privacy-Preserving Personalized Federated Learning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2506.05640","citing_title":"FedShield-LLM: A Secure and Scalable Federated Fine-Tuned Large Language Model","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03425","citing_title":"AEGIS: Scaling Long-Sequence Homomorphic Encrypted Transformer Inference via Hybrid Parallelism on Multi-GPU Systems","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27598","citing_title":"Privacy-Preserving Federated Learning via Differential Privacy and Homomorphic Encryption for Cardiovascular Disease Risk Modeling","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TSBP3DVG4T3OWEMN3OGXNFDWKB","json":"https://pith.science/pith/TSBP3DVG4T3OWEMN3OGXNFDWKB.json","graph_json":"https://pith.science/api/pith-number/TSBP3DVG4T3OWEMN3OGXNFDWKB/graph.json","events_json":"https://pith.science/api/pith-number/TSBP3DVG4T3OWEMN3OGXNFDWKB/events.json","paper":"https://pith.science/paper/TSBP3DVG"},"agent_actions":{"view_html":"https://pith.science/pith/TSBP3DVG4T3OWEMN3OGXNFDWKB","download_json":"https://pith.science/pith/TSBP3DVG4T3OWEMN3OGXNFDWKB.json","view_paper":"https://pith.science/paper/TSBP3DVG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.03152&json=true","fetch_graph":"https://pith.science/api/pith-number/TSBP3DVG4T3OWEMN3OGXNFDWKB/graph.json","fetch_events":"https://pith.science/api/pith-number/TSBP3DVG4T3OWEMN3OGXNFDWKB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSBP3DVG4T3OWEMN3OGXNFDWKB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSBP3DVG4T3OWEMN3OGXNFDWKB/action/storage_attestation","attest_author":"https://pith.science/pith/TSBP3DVG4T3OWEMN3OGXNFDWKB/action/author_attestation","sign_citation":"https://pith.science/pith/TSBP3DVG4T3OWEMN3OGXNFDWKB/action/citation_signature","submit_replication":"https://pith.science/pith/TSBP3DVG4T3OWEMN3OGXNFDWKB/action/replication_record"}},"created_at":"2026-07-05T02:35:53.926828+00:00","updated_at":"2026-07-05T02:35:53.926828+00:00"}