{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5FJ5NNUGNLEZ64AF63GLDFJ27N","short_pith_number":"pith:5FJ5NNUG","schema_version":"1.0","canonical_sha256":"e953d6b6866ac99f7005f6ccb1953afb55eac70642c37acf8a5ecea2fabc9830","source":{"kind":"arxiv","id":"2208.10134","version":3},"attestation_state":"computed","paper":{"title":"Machine Learning with Confidential Computing: A Systematization of Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Fan Mo, Hamed Haddadi, Zahra Tarkhani","submitted_at":"2022-08-22T08:23:53Z","abstract_excerpt":"Privacy and security challenges in Machine Learning (ML) have become increasingly severe, along with ML's pervasive development and the recent demonstration of large attack surfaces. As a mature system-oriented approach, Confidential Computing has been utilized in both academia and industry to mitigate privacy and security issues in various ML scenarios. In this paper, the conjunction between ML and Confidential Computing is investigated. We systematize the prior work on Confidential Computing-assisted ML techniques that provide i) confidentiality guarantees and ii) integrity assurances, and d"},"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":"2208.10134","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2022-08-22T08:23:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ff7c59f69bb88e09e2a8b60d7539352d48ea02c6adde9e246d7594bbe739546c","abstract_canon_sha256":"5cef40cb381ce43369de3130d4a340dac63b1d5eecdbc101eed07048d5a3b16e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:09.755853Z","signature_b64":"ZbuwCTZ/C1mdmVe02oYd0jHZXkoVXv9UTWBdALYNIQMyU4MC2uGSVcCG1CSQ9ajVV0PUZf7Do79AVV2qHwqMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e953d6b6866ac99f7005f6ccb1953afb55eac70642c37acf8a5ecea2fabc9830","last_reissued_at":"2026-07-05T08:26:09.754655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:09.754655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Machine Learning with Confidential Computing: A Systematization of Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Fan Mo, Hamed Haddadi, Zahra Tarkhani","submitted_at":"2022-08-22T08:23:53Z","abstract_excerpt":"Privacy and security challenges in Machine Learning (ML) have become increasingly severe, along with ML's pervasive development and the recent demonstration of large attack surfaces. As a mature system-oriented approach, Confidential Computing has been utilized in both academia and industry to mitigate privacy and security issues in various ML scenarios. In this paper, the conjunction between ML and Confidential Computing is investigated. We systematize the prior work on Confidential Computing-assisted ML techniques that provide i) confidentiality guarantees and ii) integrity assurances, and d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.10134","kind":"arxiv","version":3},"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/2208.10134/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":"2208.10134","created_at":"2026-07-05T08:26:09.754982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.10134v3","created_at":"2026-07-05T08:26:09.754982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.10134","created_at":"2026-07-05T08:26:09.754982+00:00"},{"alias_kind":"pith_short_12","alias_value":"5FJ5NNUGNLEZ","created_at":"2026-07-05T08:26:09.754982+00:00"},{"alias_kind":"pith_short_16","alias_value":"5FJ5NNUGNLEZ64AF","created_at":"2026-07-05T08:26:09.754982+00:00"},{"alias_kind":"pith_short_8","alias_value":"5FJ5NNUG","created_at":"2026-07-05T08:26:09.754982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04899","citing_title":"DIST-FL: Enhancing Security for TEE-based Aggregation in Federated Learning","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31208","citing_title":"Probing Memorization of Tabular In-Context Learning","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2404.02696","citing_title":"Deep Privacy Funnel Model: From a Discriminative to a Generative Approach with an Application to Face Recognition","ref_index":151,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5FJ5NNUGNLEZ64AF63GLDFJ27N","json":"https://pith.science/pith/5FJ5NNUGNLEZ64AF63GLDFJ27N.json","graph_json":"https://pith.science/api/pith-number/5FJ5NNUGNLEZ64AF63GLDFJ27N/graph.json","events_json":"https://pith.science/api/pith-number/5FJ5NNUGNLEZ64AF63GLDFJ27N/events.json","paper":"https://pith.science/paper/5FJ5NNUG"},"agent_actions":{"view_html":"https://pith.science/pith/5FJ5NNUGNLEZ64AF63GLDFJ27N","download_json":"https://pith.science/pith/5FJ5NNUGNLEZ64AF63GLDFJ27N.json","view_paper":"https://pith.science/paper/5FJ5NNUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.10134&json=true","fetch_graph":"https://pith.science/api/pith-number/5FJ5NNUGNLEZ64AF63GLDFJ27N/graph.json","fetch_events":"https://pith.science/api/pith-number/5FJ5NNUGNLEZ64AF63GLDFJ27N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5FJ5NNUGNLEZ64AF63GLDFJ27N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5FJ5NNUGNLEZ64AF63GLDFJ27N/action/storage_attestation","attest_author":"https://pith.science/pith/5FJ5NNUGNLEZ64AF63GLDFJ27N/action/author_attestation","sign_citation":"https://pith.science/pith/5FJ5NNUGNLEZ64AF63GLDFJ27N/action/citation_signature","submit_replication":"https://pith.science/pith/5FJ5NNUGNLEZ64AF63GLDFJ27N/action/replication_record"}},"created_at":"2026-07-05T08:26:09.754982+00:00","updated_at":"2026-07-05T08:26:09.754982+00:00"}