{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:BJWRDMKE4RIY5KZBD7FMAWFCTD","short_pith_number":"pith:BJWRDMKE","schema_version":"1.0","canonical_sha256":"0a6d11b144e4518eab211fcac058a298e0caa404cc1de3860e015d99d33bce07","source":{"kind":"arxiv","id":"1803.05961","version":1},"attestation_state":"computed","paper":{"title":"Chiron: Privacy-preserving Machine Learning as a Service","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Congzheng Song, Emmett Witchel, Reza Shokri, Tyler Hunt, Vitaly Shmatikov","submitted_at":"2018-03-15T19:27:17Z","abstract_excerpt":"Major cloud operators offer machine learning (ML) as a service, enabling customers who have the data but not ML expertise or infrastructure to train predictive models on this data. Existing ML-as-a-service platforms require users to reveal all training data to the service operator. We design, implement, and evaluate Chiron, a system for privacy-preserving machine learning as a service. First, Chiron conceals the training data from the service operator. Second, in keeping with how many existing ML-as-a-service platforms work, Chiron reveals neither the training algorithm nor the model structure"},"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":"1803.05961","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2018-03-15T19:27:17Z","cross_cats_sorted":[],"title_canon_sha256":"92cbb10321d0f9c53bf11bbd8eda040a47ad716cea37ddeaaddd0642344b7667","abstract_canon_sha256":"8c907aa8eedb1aa17ee75dd710ffcfda0c4aeb6ea33d0449d286880c23dc18ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:51.263284Z","signature_b64":"GK7R7ebPazYwu/8QhTg1KvMMuYXhsucSusWrrxHClJ3gyyheK85CzusqX2EYawJl1XE8pqsstXvQLraj/gC4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a6d11b144e4518eab211fcac058a298e0caa404cc1de3860e015d99d33bce07","last_reissued_at":"2026-05-18T00:20:51.262641Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:51.262641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chiron: Privacy-preserving Machine Learning as a Service","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Congzheng Song, Emmett Witchel, Reza Shokri, Tyler Hunt, Vitaly Shmatikov","submitted_at":"2018-03-15T19:27:17Z","abstract_excerpt":"Major cloud operators offer machine learning (ML) as a service, enabling customers who have the data but not ML expertise or infrastructure to train predictive models on this data. Existing ML-as-a-service platforms require users to reveal all training data to the service operator. We design, implement, and evaluate Chiron, a system for privacy-preserving machine learning as a service. First, Chiron conceals the training data from the service operator. Second, in keeping with how many existing ML-as-a-service platforms work, Chiron reveals neither the training algorithm nor the model structure"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.05961","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":""},"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":"1803.05961","created_at":"2026-05-18T00:20:51.262731+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.05961v1","created_at":"2026-05-18T00:20:51.262731+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.05961","created_at":"2026-05-18T00:20:51.262731+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJWRDMKE4RIY","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJWRDMKE4RIY5KZB","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJWRDMKE","created_at":"2026-05-18T12:32:16.446611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1906.09679","citing_title":"The Value of Collaboration in Convex Machine Learning with Differential Privacy","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06034","citing_title":"Towards Characterizing and Limiting Information Exposure in DNN Layers","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2508.20962","citing_title":"Characterizing Trust Boundary Vulnerabilities in TEE Containers: An Empirical Study","ref_index":129,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03213","citing_title":"When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07160","citing_title":"TENNOR: Trustworthy Execution for Neural Networks through Obliviousness and Retrievals","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04738","citing_title":"Fine-Tuning Integrity for Modern Neural Networks: Structured Drift Proofs via Norm, Rank, and Sparsity Certificates","ref_index":16,"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":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BJWRDMKE4RIY5KZBD7FMAWFCTD","json":"https://pith.science/pith/BJWRDMKE4RIY5KZBD7FMAWFCTD.json","graph_json":"https://pith.science/api/pith-number/BJWRDMKE4RIY5KZBD7FMAWFCTD/graph.json","events_json":"https://pith.science/api/pith-number/BJWRDMKE4RIY5KZBD7FMAWFCTD/events.json","paper":"https://pith.science/paper/BJWRDMKE"},"agent_actions":{"view_html":"https://pith.science/pith/BJWRDMKE4RIY5KZBD7FMAWFCTD","download_json":"https://pith.science/pith/BJWRDMKE4RIY5KZBD7FMAWFCTD.json","view_paper":"https://pith.science/paper/BJWRDMKE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.05961&json=true","fetch_graph":"https://pith.science/api/pith-number/BJWRDMKE4RIY5KZBD7FMAWFCTD/graph.json","fetch_events":"https://pith.science/api/pith-number/BJWRDMKE4RIY5KZBD7FMAWFCTD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJWRDMKE4RIY5KZBD7FMAWFCTD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJWRDMKE4RIY5KZBD7FMAWFCTD/action/storage_attestation","attest_author":"https://pith.science/pith/BJWRDMKE4RIY5KZBD7FMAWFCTD/action/author_attestation","sign_citation":"https://pith.science/pith/BJWRDMKE4RIY5KZBD7FMAWFCTD/action/citation_signature","submit_replication":"https://pith.science/pith/BJWRDMKE4RIY5KZBD7FMAWFCTD/action/replication_record"}},"created_at":"2026-05-18T00:20:51.262731+00:00","updated_at":"2026-05-18T00:20:51.262731+00:00"}