{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UU5IZBL4SO5F77EO7PAUGKQ35P","short_pith_number":"pith:UU5IZBL4","schema_version":"1.0","canonical_sha256":"a53a8c857c93ba5ffc8efbc1432a1bebc7ec68208de59a23ad5af7e350d8484e","source":{"kind":"arxiv","id":"2412.16537","version":2},"attestation_state":"computed","paper":{"title":"Accelerating Private Large Transformers Inference through Fine-grained Collaborative Computation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Bingsheng Zhang, Tianpei Lu, Yuntian Chen, Zhanyong Tang, Zheng Wang, Zhiying Shi","submitted_at":"2024-12-21T08:33:12Z","abstract_excerpt":"Homomorphic encryption (HE) and secret sharing (SS) enable computations on encrypted data, providing significant privacy benefits for large transformer-based models (TBM) in sensitive sectors like medicine and finance. However, private TBM inference incurs significant costs due to the coarse-grained application of HE and SS. We present FASTLMPI, a new approach to accelerate private TBM inference through fine-grained computation optimization. Specifically, through the fine-grained co-design of homomorphic encryption and secret sharing, FASTLMPI achieves efficient protocols for matrix multiplica"},"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":"2412.16537","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-12-21T08:33:12Z","cross_cats_sorted":[],"title_canon_sha256":"41cd651a7b74ad80a9bb7c9abdc9886964ce2d2cec54db4d405e4a5dad22df98","abstract_canon_sha256":"4099c490642e79a73d454489dd480c08e395b204aa71eb5da2b12b276a6d0d1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:26.135652Z","signature_b64":"78432hY76/FFtE/jHrZCZbUBrKccp6xoUrOC63jIbAGSM1c+mxMDGuD8XuEniZ5mt/dYfjLRR3Ho63g2aaNnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a53a8c857c93ba5ffc8efbc1432a1bebc7ec68208de59a23ad5af7e350d8484e","last_reissued_at":"2026-07-05T11:31:26.135210Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:26.135210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating Private Large Transformers Inference through Fine-grained Collaborative Computation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Bingsheng Zhang, Tianpei Lu, Yuntian Chen, Zhanyong Tang, Zheng Wang, Zhiying Shi","submitted_at":"2024-12-21T08:33:12Z","abstract_excerpt":"Homomorphic encryption (HE) and secret sharing (SS) enable computations on encrypted data, providing significant privacy benefits for large transformer-based models (TBM) in sensitive sectors like medicine and finance. However, private TBM inference incurs significant costs due to the coarse-grained application of HE and SS. We present FASTLMPI, a new approach to accelerate private TBM inference through fine-grained computation optimization. Specifically, through the fine-grained co-design of homomorphic encryption and secret sharing, FASTLMPI achieves efficient protocols for matrix multiplica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16537","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/2412.16537/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":"2412.16537","created_at":"2026-07-05T11:31:26.135265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16537v2","created_at":"2026-07-05T11:31:26.135265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16537","created_at":"2026-07-05T11:31:26.135265+00:00"},{"alias_kind":"pith_short_12","alias_value":"UU5IZBL4SO5F","created_at":"2026-07-05T11:31:26.135265+00:00"},{"alias_kind":"pith_short_16","alias_value":"UU5IZBL4SO5F77EO","created_at":"2026-07-05T11:31:26.135265+00:00"},{"alias_kind":"pith_short_8","alias_value":"UU5IZBL4","created_at":"2026-07-05T11:31:26.135265+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.19525","citing_title":"Breaking the Layer Barrier: Remodeling Private Transformer Inference with Hybrid CKKS and MPC","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UU5IZBL4SO5F77EO7PAUGKQ35P","json":"https://pith.science/pith/UU5IZBL4SO5F77EO7PAUGKQ35P.json","graph_json":"https://pith.science/api/pith-number/UU5IZBL4SO5F77EO7PAUGKQ35P/graph.json","events_json":"https://pith.science/api/pith-number/UU5IZBL4SO5F77EO7PAUGKQ35P/events.json","paper":"https://pith.science/paper/UU5IZBL4"},"agent_actions":{"view_html":"https://pith.science/pith/UU5IZBL4SO5F77EO7PAUGKQ35P","download_json":"https://pith.science/pith/UU5IZBL4SO5F77EO7PAUGKQ35P.json","view_paper":"https://pith.science/paper/UU5IZBL4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16537&json=true","fetch_graph":"https://pith.science/api/pith-number/UU5IZBL4SO5F77EO7PAUGKQ35P/graph.json","fetch_events":"https://pith.science/api/pith-number/UU5IZBL4SO5F77EO7PAUGKQ35P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UU5IZBL4SO5F77EO7PAUGKQ35P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UU5IZBL4SO5F77EO7PAUGKQ35P/action/storage_attestation","attest_author":"https://pith.science/pith/UU5IZBL4SO5F77EO7PAUGKQ35P/action/author_attestation","sign_citation":"https://pith.science/pith/UU5IZBL4SO5F77EO7PAUGKQ35P/action/citation_signature","submit_replication":"https://pith.science/pith/UU5IZBL4SO5F77EO7PAUGKQ35P/action/replication_record"}},"created_at":"2026-07-05T11:31:26.135265+00:00","updated_at":"2026-07-05T11:31:26.135265+00:00"}