{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7ECW4CWVRPAZQGEYIVMUMTJ6OI","short_pith_number":"pith:7ECW4CWV","schema_version":"1.0","canonical_sha256":"f9056e0ad58bc19818984559464d3e7235ef6676b1962b342636cc591ed7a279","source":{"kind":"arxiv","id":"2503.05850","version":1},"attestation_state":"computed","paper":{"title":"Encrypted Vector Similarity Computations Using Partially Homomorphic Encryption: Applications and Performance Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CR","authors_text":"Alper Ozpinar, Sefik Serengil","submitted_at":"2025-03-07T09:52:16Z","abstract_excerpt":"This paper explores the use of partially homomorphic encryption (PHE) for encrypted vector similarity search, with a focus on facial recognition and broader applications like reverse image search, recommendation engines, and large language models (LLMs). While fully homomorphic encryption (FHE) exists, we demonstrate that encrypted cosine similarity can be computed using PHE, offering a more practical alternative. Since PHE does not directly support cosine similarity, we propose a method that normalizes vectors in advance, enabling dot product calculations as a proxy. We also apply min-max nor"},"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":"2503.05850","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-03-07T09:52:16Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"a5077f7e646257d599dc3a699ca8a789734a9bf0e1c926cec0b272e0f5a52540","abstract_canon_sha256":"295b23a7fa7c27b6d5a89e73dc8d3e3803ca39682bd0709bdfe3ce83d279aa75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:47.984374Z","signature_b64":"irJA6ToB/37aTU/ovjjs5s6qyv6MINQODUaS3cPlh6Cj2CGVzFEuRs4rfiYoubLeM1lejyIdsX9iPllvKAxXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9056e0ad58bc19818984559464d3e7235ef6676b1962b342636cc591ed7a279","last_reissued_at":"2026-07-05T10:26:47.983817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:47.983817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Encrypted Vector Similarity Computations Using Partially Homomorphic Encryption: Applications and Performance Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CR","authors_text":"Alper Ozpinar, Sefik Serengil","submitted_at":"2025-03-07T09:52:16Z","abstract_excerpt":"This paper explores the use of partially homomorphic encryption (PHE) for encrypted vector similarity search, with a focus on facial recognition and broader applications like reverse image search, recommendation engines, and large language models (LLMs). While fully homomorphic encryption (FHE) exists, we demonstrate that encrypted cosine similarity can be computed using PHE, offering a more practical alternative. Since PHE does not directly support cosine similarity, we propose a method that normalizes vectors in advance, enabling dot product calculations as a proxy. We also apply min-max nor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05850","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/2503.05850/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":"2503.05850","created_at":"2026-07-05T10:26:47.983916+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.05850v1","created_at":"2026-07-05T10:26:47.983916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05850","created_at":"2026-07-05T10:26:47.983916+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ECW4CWVRPAZ","created_at":"2026-07-05T10:26:47.983916+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ECW4CWVRPAZQGEY","created_at":"2026-07-05T10:26:47.983916+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ECW4CWV","created_at":"2026-07-05T10:26:47.983916+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.28700","citing_title":"Bridging the Gap Between PHE and FHE: A Performance and Trade-off Analysis of The Somewhat Homomorphic BGN Cryptosystem","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7ECW4CWVRPAZQGEYIVMUMTJ6OI","json":"https://pith.science/pith/7ECW4CWVRPAZQGEYIVMUMTJ6OI.json","graph_json":"https://pith.science/api/pith-number/7ECW4CWVRPAZQGEYIVMUMTJ6OI/graph.json","events_json":"https://pith.science/api/pith-number/7ECW4CWVRPAZQGEYIVMUMTJ6OI/events.json","paper":"https://pith.science/paper/7ECW4CWV"},"agent_actions":{"view_html":"https://pith.science/pith/7ECW4CWVRPAZQGEYIVMUMTJ6OI","download_json":"https://pith.science/pith/7ECW4CWVRPAZQGEYIVMUMTJ6OI.json","view_paper":"https://pith.science/paper/7ECW4CWV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.05850&json=true","fetch_graph":"https://pith.science/api/pith-number/7ECW4CWVRPAZQGEYIVMUMTJ6OI/graph.json","fetch_events":"https://pith.science/api/pith-number/7ECW4CWVRPAZQGEYIVMUMTJ6OI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ECW4CWVRPAZQGEYIVMUMTJ6OI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ECW4CWVRPAZQGEYIVMUMTJ6OI/action/storage_attestation","attest_author":"https://pith.science/pith/7ECW4CWVRPAZQGEYIVMUMTJ6OI/action/author_attestation","sign_citation":"https://pith.science/pith/7ECW4CWVRPAZQGEYIVMUMTJ6OI/action/citation_signature","submit_replication":"https://pith.science/pith/7ECW4CWVRPAZQGEYIVMUMTJ6OI/action/replication_record"}},"created_at":"2026-07-05T10:26:47.983916+00:00","updated_at":"2026-07-05T10:26:47.983916+00:00"}