{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BYNORHJWPFYNVDW7RXLGWA3NQ7","short_pith_number":"pith:BYNORHJW","schema_version":"1.0","canonical_sha256":"0e1ae89d367970da8edf8dd66b036d87e73ecc32f5597f0dfcef091c08c00252","source":{"kind":"arxiv","id":"2309.01243","version":4},"attestation_state":"computed","paper":{"title":"The Normal Distributions Indistinguishability Spectrum and its Application to Privacy-Preserving Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Malik Magdon-Ismail, Vassilis Zikas, Yun Lu, Yu Wei","submitted_at":"2023-09-03T19:07:31Z","abstract_excerpt":"We investigate the privacy of {\\em any} algorithm whose outputs have Gaussian distribution. This work is motivated by the prevalence of such algorithms in several useful (ML) applications, and the comparatively little research that focuses on privacy-preserving learning outside of adding Gaussian noise to the data (such as DP-SGD).\n  {\\em What is the DP of any algorithm with multivariate Gaussian output?}\n  We answer the above research question with a general lemma which we call {\\em Normal Distributions Indistinguishability Spectrum} (NDIS), a closed-form analytic computation of the hockey-st"},"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":"2309.01243","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2023-09-03T19:07:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b8f75b85e8ecd1ce643d52c22cf4b18de86e8c52696a82c492814b2dd099e40f","abstract_canon_sha256":"f3ad538a40bc674b53f4cc667fd9725344dfc827c93e9c5c4496c909a4c1d6a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:24.539754Z","signature_b64":"4alX9RMQGpWX4FX/Eoj5L+QfsEDpHcgLxNA4XauwvSLvBOy2myVH9QjT93pM42WQ740W/Nkt9K0ywfTv1TSvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e1ae89d367970da8edf8dd66b036d87e73ecc32f5597f0dfcef091c08c00252","last_reissued_at":"2026-05-20T00:05:24.538869Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:24.538869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Normal Distributions Indistinguishability Spectrum and its Application to Privacy-Preserving Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Malik Magdon-Ismail, Vassilis Zikas, Yun Lu, Yu Wei","submitted_at":"2023-09-03T19:07:31Z","abstract_excerpt":"We investigate the privacy of {\\em any} algorithm whose outputs have Gaussian distribution. This work is motivated by the prevalence of such algorithms in several useful (ML) applications, and the comparatively little research that focuses on privacy-preserving learning outside of adding Gaussian noise to the data (such as DP-SGD).\n  {\\em What is the DP of any algorithm with multivariate Gaussian output?}\n  We answer the above research question with a general lemma which we call {\\em Normal Distributions Indistinguishability Spectrum} (NDIS), a closed-form analytic computation of the hockey-st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01243","kind":"arxiv","version":4},"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/2309.01243/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":"2309.01243","created_at":"2026-05-20T00:05:24.538994+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.01243v4","created_at":"2026-05-20T00:05:24.538994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01243","created_at":"2026-05-20T00:05:24.538994+00:00"},{"alias_kind":"pith_short_12","alias_value":"BYNORHJWPFYN","created_at":"2026-05-20T00:05:24.538994+00:00"},{"alias_kind":"pith_short_16","alias_value":"BYNORHJWPFYNVDW7","created_at":"2026-05-20T00:05:24.538994+00:00"},{"alias_kind":"pith_short_8","alias_value":"BYNORHJW","created_at":"2026-05-20T00:05:24.538994+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/BYNORHJWPFYNVDW7RXLGWA3NQ7","json":"https://pith.science/pith/BYNORHJWPFYNVDW7RXLGWA3NQ7.json","graph_json":"https://pith.science/api/pith-number/BYNORHJWPFYNVDW7RXLGWA3NQ7/graph.json","events_json":"https://pith.science/api/pith-number/BYNORHJWPFYNVDW7RXLGWA3NQ7/events.json","paper":"https://pith.science/paper/BYNORHJW"},"agent_actions":{"view_html":"https://pith.science/pith/BYNORHJWPFYNVDW7RXLGWA3NQ7","download_json":"https://pith.science/pith/BYNORHJWPFYNVDW7RXLGWA3NQ7.json","view_paper":"https://pith.science/paper/BYNORHJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.01243&json=true","fetch_graph":"https://pith.science/api/pith-number/BYNORHJWPFYNVDW7RXLGWA3NQ7/graph.json","fetch_events":"https://pith.science/api/pith-number/BYNORHJWPFYNVDW7RXLGWA3NQ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BYNORHJWPFYNVDW7RXLGWA3NQ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BYNORHJWPFYNVDW7RXLGWA3NQ7/action/storage_attestation","attest_author":"https://pith.science/pith/BYNORHJWPFYNVDW7RXLGWA3NQ7/action/author_attestation","sign_citation":"https://pith.science/pith/BYNORHJWPFYNVDW7RXLGWA3NQ7/action/citation_signature","submit_replication":"https://pith.science/pith/BYNORHJWPFYNVDW7RXLGWA3NQ7/action/replication_record"}},"created_at":"2026-05-20T00:05:24.538994+00:00","updated_at":"2026-05-20T00:05:24.538994+00:00"}