{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:I4GL6DWDI3HDDMWSZTXKTDSTIP","short_pith_number":"pith:I4GL6DWD","schema_version":"1.0","canonical_sha256":"470cbf0ec346ce31b2d2cceea98e5343ca11cd2a89daa9f77e4f46ad44526519","source":{"kind":"arxiv","id":"1912.03485","version":1},"attestation_state":"computed","paper":{"title":"Privacy-Preserving Inference in Machine Learning Services Using Trusted Execution Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Keshav Balasubramaniam, Krishna Giri Narra, Murali Annavaram, Yongqin Wang, Zhifeng Lin","submitted_at":"2019-12-07T10:27:33Z","abstract_excerpt":"This work presents Origami, which provides privacy-preserving inference for large deep neural network (DNN) models through a combination of enclave execution, cryptographic blinding, interspersed with accelerator-based computation. Origami partitions the ML model into multiple partitions. The first partition receives the encrypted user input within an SGX enclave. The enclave decrypts the input and then applies cryptographic blinding to the input data and the model parameters. Cryptographic blinding is a technique that adds noise to obfuscate data. Origami sends the obfuscated data for computa"},"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":"1912.03485","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-07T10:27:33Z","cross_cats_sorted":["cs.CR","cs.CV","stat.ML"],"title_canon_sha256":"2cf420012366235b64ab3038aee12e1de428046aa46c62a67c9d5d3565919dcc","abstract_canon_sha256":"fb28b475c74634b51590eee0c79039c95f7e33b49b952981640f8f728daaafc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:24:46.087596Z","signature_b64":"VynTO50TLxOAfaz/SbZmEIqoLqde8pyz18b4XnzZzMYTQ2HKEZK8UuozC9woHYIpY3vjCVYNQ8C4W8ZT0+ZnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"470cbf0ec346ce31b2d2cceea98e5343ca11cd2a89daa9f77e4f46ad44526519","last_reissued_at":"2026-07-05T00:24:46.087126Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:24:46.087126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Privacy-Preserving Inference in Machine Learning Services Using Trusted Execution Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Keshav Balasubramaniam, Krishna Giri Narra, Murali Annavaram, Yongqin Wang, Zhifeng Lin","submitted_at":"2019-12-07T10:27:33Z","abstract_excerpt":"This work presents Origami, which provides privacy-preserving inference for large deep neural network (DNN) models through a combination of enclave execution, cryptographic blinding, interspersed with accelerator-based computation. Origami partitions the ML model into multiple partitions. The first partition receives the encrypted user input within an SGX enclave. The enclave decrypts the input and then applies cryptographic blinding to the input data and the model parameters. Cryptographic blinding is a technique that adds noise to obfuscate data. Origami sends the obfuscated data for computa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.03485","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/1912.03485/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":"1912.03485","created_at":"2026-07-05T00:24:46.087190+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.03485v1","created_at":"2026-07-05T00:24:46.087190+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.03485","created_at":"2026-07-05T00:24:46.087190+00:00"},{"alias_kind":"pith_short_12","alias_value":"I4GL6DWDI3HD","created_at":"2026-07-05T00:24:46.087190+00:00"},{"alias_kind":"pith_short_16","alias_value":"I4GL6DWDI3HDDMWS","created_at":"2026-07-05T00:24:46.087190+00:00"},{"alias_kind":"pith_short_8","alias_value":"I4GL6DWD","created_at":"2026-07-05T00:24:46.087190+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I4GL6DWDI3HDDMWSZTXKTDSTIP","json":"https://pith.science/pith/I4GL6DWDI3HDDMWSZTXKTDSTIP.json","graph_json":"https://pith.science/api/pith-number/I4GL6DWDI3HDDMWSZTXKTDSTIP/graph.json","events_json":"https://pith.science/api/pith-number/I4GL6DWDI3HDDMWSZTXKTDSTIP/events.json","paper":"https://pith.science/paper/I4GL6DWD"},"agent_actions":{"view_html":"https://pith.science/pith/I4GL6DWDI3HDDMWSZTXKTDSTIP","download_json":"https://pith.science/pith/I4GL6DWDI3HDDMWSZTXKTDSTIP.json","view_paper":"https://pith.science/paper/I4GL6DWD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.03485&json=true","fetch_graph":"https://pith.science/api/pith-number/I4GL6DWDI3HDDMWSZTXKTDSTIP/graph.json","fetch_events":"https://pith.science/api/pith-number/I4GL6DWDI3HDDMWSZTXKTDSTIP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I4GL6DWDI3HDDMWSZTXKTDSTIP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I4GL6DWDI3HDDMWSZTXKTDSTIP/action/storage_attestation","attest_author":"https://pith.science/pith/I4GL6DWDI3HDDMWSZTXKTDSTIP/action/author_attestation","sign_citation":"https://pith.science/pith/I4GL6DWDI3HDDMWSZTXKTDSTIP/action/citation_signature","submit_replication":"https://pith.science/pith/I4GL6DWDI3HDDMWSZTXKTDSTIP/action/replication_record"}},"created_at":"2026-07-05T00:24:46.087190+00:00","updated_at":"2026-07-05T00:24:46.087190+00:00"}