{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QIET5J7T4YTNBMXJNRO6JEBQDC","short_pith_number":"pith:QIET5J7T","schema_version":"1.0","canonical_sha256":"82093ea7f3e626d0b2e96c5de4903018bc88f7b79600c81b3647356eeb2efa46","source":{"kind":"arxiv","id":"2303.07152","version":2},"attestation_state":"computed","paper":{"title":"Score Attack: A Lower Bound Technique for Optimal Differentially Private Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG","stat.ME","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Linjun Zhang, T. Tony Cai, Yichen Wang","submitted_at":"2023-03-13T14:26:27Z","abstract_excerpt":"Achieving optimal statistical performance while ensuring the privacy of personal data is a challenging yet crucial objective in modern data analysis. However, characterizing the optimality, particularly the minimax lower bound, under privacy constraints is technically difficult. To address this issue, we propose a novel approach called the score attack, which provides a lower bound on the differential-privacy-constrained minimax risk of parameter estimation. The score attack method is based on the tracing attack concept in differential privacy and can be applied to any statistical model with a"},"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":"2303.07152","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2023-03-13T14:26:27Z","cross_cats_sorted":["cs.CR","cs.LG","stat.ME","stat.ML","stat.TH"],"title_canon_sha256":"781b3960715b951b822e4e14a6db07e96d5d879d26097c5d86e8f5c57ed86dbd","abstract_canon_sha256":"03439f8c9570dc1e28b233f0b5247eefbd5a48bba5038b1cdc56c946b5f5c3db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:47.617629Z","signature_b64":"ETit7VRVBN5bCJoTgxnugIPpXgTcSZM5Wq3veyAZTkg2Pa0xV7rz4pq8aOqiYa0RBkFcbUodwlE2ICphfSvbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82093ea7f3e626d0b2e96c5de4903018bc88f7b79600c81b3647356eeb2efa46","last_reissued_at":"2026-07-05T11:35:47.617158Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:47.617158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Score Attack: A Lower Bound Technique for Optimal Differentially Private Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG","stat.ME","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Linjun Zhang, T. Tony Cai, Yichen Wang","submitted_at":"2023-03-13T14:26:27Z","abstract_excerpt":"Achieving optimal statistical performance while ensuring the privacy of personal data is a challenging yet crucial objective in modern data analysis. However, characterizing the optimality, particularly the minimax lower bound, under privacy constraints is technically difficult. To address this issue, we propose a novel approach called the score attack, which provides a lower bound on the differential-privacy-constrained minimax risk of parameter estimation. The score attack method is based on the tracing attack concept in differential privacy and can be applied to any statistical model with a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07152","kind":"arxiv","version":2},"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/2303.07152/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":"2303.07152","created_at":"2026-07-05T11:35:47.617217+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.07152v2","created_at":"2026-07-05T11:35:47.617217+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07152","created_at":"2026-07-05T11:35:47.617217+00:00"},{"alias_kind":"pith_short_12","alias_value":"QIET5J7T4YTN","created_at":"2026-07-05T11:35:47.617217+00:00"},{"alias_kind":"pith_short_16","alias_value":"QIET5J7T4YTNBMXJ","created_at":"2026-07-05T11:35:47.617217+00:00"},{"alias_kind":"pith_short_8","alias_value":"QIET5J7T","created_at":"2026-07-05T11:35:47.617217+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21860","citing_title":"Robust Statistical Estimators with Bounded Empirical Sensitivity","ref_index":255,"is_internal_anchor":false},{"citing_arxiv_id":"2505.16329","citing_title":"High-Dimensional Private Linear Regression with Optimal Rates","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19813","citing_title":"A Van Trees Lower Bound for Fully Interactive Differentially Private Federated Learning","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QIET5J7T4YTNBMXJNRO6JEBQDC","json":"https://pith.science/pith/QIET5J7T4YTNBMXJNRO6JEBQDC.json","graph_json":"https://pith.science/api/pith-number/QIET5J7T4YTNBMXJNRO6JEBQDC/graph.json","events_json":"https://pith.science/api/pith-number/QIET5J7T4YTNBMXJNRO6JEBQDC/events.json","paper":"https://pith.science/paper/QIET5J7T"},"agent_actions":{"view_html":"https://pith.science/pith/QIET5J7T4YTNBMXJNRO6JEBQDC","download_json":"https://pith.science/pith/QIET5J7T4YTNBMXJNRO6JEBQDC.json","view_paper":"https://pith.science/paper/QIET5J7T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.07152&json=true","fetch_graph":"https://pith.science/api/pith-number/QIET5J7T4YTNBMXJNRO6JEBQDC/graph.json","fetch_events":"https://pith.science/api/pith-number/QIET5J7T4YTNBMXJNRO6JEBQDC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QIET5J7T4YTNBMXJNRO6JEBQDC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QIET5J7T4YTNBMXJNRO6JEBQDC/action/storage_attestation","attest_author":"https://pith.science/pith/QIET5J7T4YTNBMXJNRO6JEBQDC/action/author_attestation","sign_citation":"https://pith.science/pith/QIET5J7T4YTNBMXJNRO6JEBQDC/action/citation_signature","submit_replication":"https://pith.science/pith/QIET5J7T4YTNBMXJNRO6JEBQDC/action/replication_record"}},"created_at":"2026-07-05T11:35:47.617217+00:00","updated_at":"2026-07-05T11:35:47.617217+00:00"}