{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DCMPTJEHZJOLQ4NRTQJ7XVEPXY","short_pith_number":"pith:DCMPTJEH","schema_version":"1.0","canonical_sha256":"1898f9a487ca5cb871b19c13fbd48fbe2ccda9055b6f685ce3cd310d513e0557","source":{"kind":"arxiv","id":"2412.08145","version":1},"attestation_state":"computed","paper":{"title":"A Survey on Private Transformer Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Jun Zhao, Liangxin Qian, Xinyu Zhou, Yang Li, Yitong Wang","submitted_at":"2024-12-11T07:05:24Z","abstract_excerpt":"Transformer models have revolutionized AI, enabling applications like content generation and sentiment analysis. However, their use in Machine Learning as a Service (MLaaS) raises significant privacy concerns, as centralized servers process sensitive user data. Private Transformer Inference (PTI) addresses these issues using cryptographic techniques such as Secure Multi-Party Computation (MPC) and Homomorphic Encryption (HE), enabling secure model inference without exposing inputs or models. This paper reviews recent advancements in PTI, analyzing state-of-the-art solutions, their challenges, "},"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":"2412.08145","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-12-11T07:05:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b11717999bab44aa7e541c385047358bbb314e88cf3fa6126ab56a1036fa48a9","abstract_canon_sha256":"28e7edbdb411490705163b34dff9983c76d7ee7291e9535b745354302552e9a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:45.039358Z","signature_b64":"JRuFnWzBNSU4NfkmB+vfbBN8XAVhUzqbWTy46ONoGwoo6EYrjfV9S7vo9FAB4xic9DmhANirnGTxTzLo/iOKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1898f9a487ca5cb871b19c13fbd48fbe2ccda9055b6f685ce3cd310d513e0557","last_reissued_at":"2026-07-05T09:47:45.038943Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:45.038943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Private Transformer Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Jun Zhao, Liangxin Qian, Xinyu Zhou, Yang Li, Yitong Wang","submitted_at":"2024-12-11T07:05:24Z","abstract_excerpt":"Transformer models have revolutionized AI, enabling applications like content generation and sentiment analysis. However, their use in Machine Learning as a Service (MLaaS) raises significant privacy concerns, as centralized servers process sensitive user data. Private Transformer Inference (PTI) addresses these issues using cryptographic techniques such as Secure Multi-Party Computation (MPC) and Homomorphic Encryption (HE), enabling secure model inference without exposing inputs or models. This paper reviews recent advancements in PTI, analyzing state-of-the-art solutions, their challenges, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08145","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/2412.08145/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":"2412.08145","created_at":"2026-07-05T09:47:45.039001+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08145v1","created_at":"2026-07-05T09:47:45.039001+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08145","created_at":"2026-07-05T09:47:45.039001+00:00"},{"alias_kind":"pith_short_12","alias_value":"DCMPTJEHZJOL","created_at":"2026-07-05T09:47:45.039001+00:00"},{"alias_kind":"pith_short_16","alias_value":"DCMPTJEHZJOLQ4NR","created_at":"2026-07-05T09:47:45.039001+00:00"},{"alias_kind":"pith_short_8","alias_value":"DCMPTJEH","created_at":"2026-07-05T09:47:45.039001+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03213","citing_title":"When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03213","citing_title":"When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DCMPTJEHZJOLQ4NRTQJ7XVEPXY","json":"https://pith.science/pith/DCMPTJEHZJOLQ4NRTQJ7XVEPXY.json","graph_json":"https://pith.science/api/pith-number/DCMPTJEHZJOLQ4NRTQJ7XVEPXY/graph.json","events_json":"https://pith.science/api/pith-number/DCMPTJEHZJOLQ4NRTQJ7XVEPXY/events.json","paper":"https://pith.science/paper/DCMPTJEH"},"agent_actions":{"view_html":"https://pith.science/pith/DCMPTJEHZJOLQ4NRTQJ7XVEPXY","download_json":"https://pith.science/pith/DCMPTJEHZJOLQ4NRTQJ7XVEPXY.json","view_paper":"https://pith.science/paper/DCMPTJEH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08145&json=true","fetch_graph":"https://pith.science/api/pith-number/DCMPTJEHZJOLQ4NRTQJ7XVEPXY/graph.json","fetch_events":"https://pith.science/api/pith-number/DCMPTJEHZJOLQ4NRTQJ7XVEPXY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DCMPTJEHZJOLQ4NRTQJ7XVEPXY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DCMPTJEHZJOLQ4NRTQJ7XVEPXY/action/storage_attestation","attest_author":"https://pith.science/pith/DCMPTJEHZJOLQ4NRTQJ7XVEPXY/action/author_attestation","sign_citation":"https://pith.science/pith/DCMPTJEHZJOLQ4NRTQJ7XVEPXY/action/citation_signature","submit_replication":"https://pith.science/pith/DCMPTJEHZJOLQ4NRTQJ7XVEPXY/action/replication_record"}},"created_at":"2026-07-05T09:47:45.039001+00:00","updated_at":"2026-07-05T09:47:45.039001+00:00"}