{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5X23OLYVJCSKQ225W2FQSEKMOZ","short_pith_number":"pith:5X23OLYV","schema_version":"1.0","canonical_sha256":"edf5b72f1548a4a86b5db68b09114c764f1ebc6b20baa88858879d33bdf47b50","source":{"kind":"arxiv","id":"2401.16583","version":1},"attestation_state":"computed","paper":{"title":"Data-Oblivious ML Accelerators using Hardware Security Extensions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Hossam ElAtali, John Z. Jekel, Lachlan J. Gunn, N. Asokan","submitted_at":"2024-01-29T21:34:29Z","abstract_excerpt":"Outsourced computation can put client data confidentiality at risk. Existing solutions are either inefficient or insufficiently secure: cryptographic techniques like fully-homomorphic encryption incur significant overheads, even with hardware assistance, while the complexity of hardware-assisted trusted execution environments has been exploited to leak secret data.\n  Recent proposals such as BliMe and OISA show how dynamic information flow tracking (DIFT) enforced in hardware can protect client data efficiently. They are designed to protect CPU-only workloads. However, many outsourced computin"},"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":"2401.16583","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-01-29T21:34:29Z","cross_cats_sorted":[],"title_canon_sha256":"1a921bb00e57e8f43446e45a9edc0c72bd8671b8780bd07477c8c228786080d7","abstract_canon_sha256":"aef01437d824147628f2fc9af2344d9649ae8cda1b979feafc36cd56eefc0c0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:21.908553Z","signature_b64":"iaKcvQ2rdkKfuol1mtqAlRwHIHL+wp0MMXLkh5gulIs08ue0VPxxQS3hC8SUxWWlH8ahyjfHG3pBhI25lXKTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edf5b72f1548a4a86b5db68b09114c764f1ebc6b20baa88858879d33bdf47b50","last_reissued_at":"2026-07-05T08:36:21.908076Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:21.908076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Oblivious ML Accelerators using Hardware Security Extensions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Hossam ElAtali, John Z. Jekel, Lachlan J. Gunn, N. Asokan","submitted_at":"2024-01-29T21:34:29Z","abstract_excerpt":"Outsourced computation can put client data confidentiality at risk. Existing solutions are either inefficient or insufficiently secure: cryptographic techniques like fully-homomorphic encryption incur significant overheads, even with hardware assistance, while the complexity of hardware-assisted trusted execution environments has been exploited to leak secret data.\n  Recent proposals such as BliMe and OISA show how dynamic information flow tracking (DIFT) enforced in hardware can protect client data efficiently. They are designed to protect CPU-only workloads. However, many outsourced computin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16583","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/2401.16583/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":"2401.16583","created_at":"2026-07-05T08:36:21.908141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.16583v1","created_at":"2026-07-05T08:36:21.908141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16583","created_at":"2026-07-05T08:36:21.908141+00:00"},{"alias_kind":"pith_short_12","alias_value":"5X23OLYVJCSK","created_at":"2026-07-05T08:36:21.908141+00:00"},{"alias_kind":"pith_short_16","alias_value":"5X23OLYVJCSKQ225","created_at":"2026-07-05T08:36:21.908141+00:00"},{"alias_kind":"pith_short_8","alias_value":"5X23OLYV","created_at":"2026-07-05T08:36:21.908141+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02794","citing_title":"Edge-Efficient Image Restoration: Transformer Distillation into State-Space Models","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5X23OLYVJCSKQ225W2FQSEKMOZ","json":"https://pith.science/pith/5X23OLYVJCSKQ225W2FQSEKMOZ.json","graph_json":"https://pith.science/api/pith-number/5X23OLYVJCSKQ225W2FQSEKMOZ/graph.json","events_json":"https://pith.science/api/pith-number/5X23OLYVJCSKQ225W2FQSEKMOZ/events.json","paper":"https://pith.science/paper/5X23OLYV"},"agent_actions":{"view_html":"https://pith.science/pith/5X23OLYVJCSKQ225W2FQSEKMOZ","download_json":"https://pith.science/pith/5X23OLYVJCSKQ225W2FQSEKMOZ.json","view_paper":"https://pith.science/paper/5X23OLYV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.16583&json=true","fetch_graph":"https://pith.science/api/pith-number/5X23OLYVJCSKQ225W2FQSEKMOZ/graph.json","fetch_events":"https://pith.science/api/pith-number/5X23OLYVJCSKQ225W2FQSEKMOZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5X23OLYVJCSKQ225W2FQSEKMOZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5X23OLYVJCSKQ225W2FQSEKMOZ/action/storage_attestation","attest_author":"https://pith.science/pith/5X23OLYVJCSKQ225W2FQSEKMOZ/action/author_attestation","sign_citation":"https://pith.science/pith/5X23OLYVJCSKQ225W2FQSEKMOZ/action/citation_signature","submit_replication":"https://pith.science/pith/5X23OLYVJCSKQ225W2FQSEKMOZ/action/replication_record"}},"created_at":"2026-07-05T08:36:21.908141+00:00","updated_at":"2026-07-05T08:36:21.908141+00:00"}