{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5A4JHR7Z437M2Y54SE7A3HS6XO","short_pith_number":"pith:5A4JHR7Z","schema_version":"1.0","canonical_sha256":"e83893c7f9e6fecd63bc913e0d9e5ebb948be0e50ef15761050803cd9e2715aa","source":{"kind":"arxiv","id":"2509.08704","version":1},"attestation_state":"computed","paper":{"title":"Tight Privacy Audit in One Run","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Di Wang, Hanshen Xiao, Tianhao Wang, Yuan Tian, Zihang Xiang","submitted_at":"2025-09-10T15:55:03Z","abstract_excerpt":"In this paper, we study the problem of privacy audit in one run and show that our method achieves tight audit results for various differentially private protocols. This includes obtaining tight results for auditing $(\\varepsilon,\\delta)$-DP algorithms where all previous work fails to achieve in any parameter setups. We first formulate a framework for privacy audit \\textit{in one run} with refinement compared with previous work. Then, based on modeling privacy by the $f$-DP formulation, we study the implications of our framework to obtain a theoretically justified lower bound for privacy audit."},"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":"2509.08704","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-09-10T15:55:03Z","cross_cats_sorted":[],"title_canon_sha256":"06862893b8fc813a7a328edd3ddb1621d97fded458657a166fe1d006f5cfba8c","abstract_canon_sha256":"bba97581c43facfbdfa7aa392bb46cf83ab46e4d541af0c9b7ef9373a6ade116"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:34.544675Z","signature_b64":"48dQ+KtaBzqlDk4Ywz1dli5nm9YSy2t62HzClZw0pVFAyBOjiKQ2hSGdjuCqu6TVR9f1bW+5L8UQfY649ZPiCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e83893c7f9e6fecd63bc913e0d9e5ebb948be0e50ef15761050803cd9e2715aa","last_reissued_at":"2026-07-05T12:08:34.544124Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:34.544124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tight Privacy Audit in One Run","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Di Wang, Hanshen Xiao, Tianhao Wang, Yuan Tian, Zihang Xiang","submitted_at":"2025-09-10T15:55:03Z","abstract_excerpt":"In this paper, we study the problem of privacy audit in one run and show that our method achieves tight audit results for various differentially private protocols. This includes obtaining tight results for auditing $(\\varepsilon,\\delta)$-DP algorithms where all previous work fails to achieve in any parameter setups. We first formulate a framework for privacy audit \\textit{in one run} with refinement compared with previous work. Then, based on modeling privacy by the $f$-DP formulation, we study the implications of our framework to obtain a theoretically justified lower bound for privacy audit."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08704","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/2509.08704/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":"2509.08704","created_at":"2026-07-05T12:08:34.544186+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.08704v1","created_at":"2026-07-05T12:08:34.544186+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08704","created_at":"2026-07-05T12:08:34.544186+00:00"},{"alias_kind":"pith_short_12","alias_value":"5A4JHR7Z437M","created_at":"2026-07-05T12:08:34.544186+00:00"},{"alias_kind":"pith_short_16","alias_value":"5A4JHR7Z437M2Y54","created_at":"2026-07-05T12:08:34.544186+00:00"},{"alias_kind":"pith_short_8","alias_value":"5A4JHR7Z","created_at":"2026-07-05T12:08:34.544186+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12733","citing_title":"Let's Ask Gauss: Improved One-Run Privacy Auditing","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15648","citing_title":"Rethinking the Security of DP-SGD: A Corrected Analysis of Differentially Private Machine Learning","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5A4JHR7Z437M2Y54SE7A3HS6XO","json":"https://pith.science/pith/5A4JHR7Z437M2Y54SE7A3HS6XO.json","graph_json":"https://pith.science/api/pith-number/5A4JHR7Z437M2Y54SE7A3HS6XO/graph.json","events_json":"https://pith.science/api/pith-number/5A4JHR7Z437M2Y54SE7A3HS6XO/events.json","paper":"https://pith.science/paper/5A4JHR7Z"},"agent_actions":{"view_html":"https://pith.science/pith/5A4JHR7Z437M2Y54SE7A3HS6XO","download_json":"https://pith.science/pith/5A4JHR7Z437M2Y54SE7A3HS6XO.json","view_paper":"https://pith.science/paper/5A4JHR7Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.08704&json=true","fetch_graph":"https://pith.science/api/pith-number/5A4JHR7Z437M2Y54SE7A3HS6XO/graph.json","fetch_events":"https://pith.science/api/pith-number/5A4JHR7Z437M2Y54SE7A3HS6XO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5A4JHR7Z437M2Y54SE7A3HS6XO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5A4JHR7Z437M2Y54SE7A3HS6XO/action/storage_attestation","attest_author":"https://pith.science/pith/5A4JHR7Z437M2Y54SE7A3HS6XO/action/author_attestation","sign_citation":"https://pith.science/pith/5A4JHR7Z437M2Y54SE7A3HS6XO/action/citation_signature","submit_replication":"https://pith.science/pith/5A4JHR7Z437M2Y54SE7A3HS6XO/action/replication_record"}},"created_at":"2026-07-05T12:08:34.544186+00:00","updated_at":"2026-07-05T12:08:34.544186+00:00"}