{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FS5WDJ7ZDHRWGCV2WHX6RHYGLK","short_pith_number":"pith:FS5WDJ7Z","schema_version":"1.0","canonical_sha256":"2cbb61a7f919e3630abab1efe89f065a8132cab26504cbf33452cc34ce67a15d","source":{"kind":"arxiv","id":"2502.07066","version":2},"attestation_state":"computed","paper":{"title":"General-Purpose $f$-DP Estimation and Auditing in a Black-Box Setting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ME","stat.TH"],"primary_cat":"cs.CR","authors_text":"(2) Aarhus University, (3) University of Victoria, (4) Georgia Institute of Technology), Holger Dette (1), Martin Dunsche (1), \\\"Onder Askin (1), Tim Kutta (2), Vassilis Zikas (4) ((1) Ruhr-University Bochum, Yun Lu (3), Yu Wei (4)","submitted_at":"2025-02-10T21:58:17Z","abstract_excerpt":"In this paper we propose new methods to statistically assess $f$-Differential Privacy ($f$-DP), a recent refinement of differential privacy (DP) that remedies certain weaknesses of standard DP (including tightness under algorithmic composition). A challenge when deploying differentially private mechanisms is that DP is hard to validate, especially in the black-box setting. This has led to numerous empirical methods for auditing standard DP, while $f$-DP remains less explored. We introduce new black-box methods for $f$-DP that, unlike existing approaches for this privacy notion, do not require "},"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":"2502.07066","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-02-10T21:58:17Z","cross_cats_sorted":["math.ST","stat.ME","stat.TH"],"title_canon_sha256":"727b1fc2fb52ce0fbb4d15f6c644c8039e87472543cbe1b2175494e2561f60e6","abstract_canon_sha256":"b9795871effc1b660b4aff41471e7b0b41f1e18df87307ac97a137d7b3ea63df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:50.698857Z","signature_b64":"6isn5x9GJBz+XhgQvSuh7q9oiQ9qDBYnTSscesNVZXldsP3CQpqCwb1jQ+Nl8zsk99knEfhulX5hROEzGLK5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cbb61a7f919e3630abab1efe89f065a8132cab26504cbf33452cc34ce67a15d","last_reissued_at":"2026-07-05T11:20:50.698339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:50.698339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"General-Purpose $f$-DP Estimation and Auditing in a Black-Box Setting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ME","stat.TH"],"primary_cat":"cs.CR","authors_text":"(2) Aarhus University, (3) University of Victoria, (4) Georgia Institute of Technology), Holger Dette (1), Martin Dunsche (1), \\\"Onder Askin (1), Tim Kutta (2), Vassilis Zikas (4) ((1) Ruhr-University Bochum, Yun Lu (3), Yu Wei (4)","submitted_at":"2025-02-10T21:58:17Z","abstract_excerpt":"In this paper we propose new methods to statistically assess $f$-Differential Privacy ($f$-DP), a recent refinement of differential privacy (DP) that remedies certain weaknesses of standard DP (including tightness under algorithmic composition). A challenge when deploying differentially private mechanisms is that DP is hard to validate, especially in the black-box setting. This has led to numerous empirical methods for auditing standard DP, while $f$-DP remains less explored. We introduce new black-box methods for $f$-DP that, unlike existing approaches for this privacy notion, do not require "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07066","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/2502.07066/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":"2502.07066","created_at":"2026-07-05T11:20:50.698405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.07066v2","created_at":"2026-07-05T11:20:50.698405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07066","created_at":"2026-07-05T11:20:50.698405+00:00"},{"alias_kind":"pith_short_12","alias_value":"FS5WDJ7ZDHRW","created_at":"2026-07-05T11:20:50.698405+00:00"},{"alias_kind":"pith_short_16","alias_value":"FS5WDJ7ZDHRWGCV2","created_at":"2026-07-05T11:20:50.698405+00:00"},{"alias_kind":"pith_short_8","alias_value":"FS5WDJ7Z","created_at":"2026-07-05T11:20:50.698405+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12733","citing_title":"Let's Ask Gauss: Improved One-Run Privacy Auditing","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FS5WDJ7ZDHRWGCV2WHX6RHYGLK","json":"https://pith.science/pith/FS5WDJ7ZDHRWGCV2WHX6RHYGLK.json","graph_json":"https://pith.science/api/pith-number/FS5WDJ7ZDHRWGCV2WHX6RHYGLK/graph.json","events_json":"https://pith.science/api/pith-number/FS5WDJ7ZDHRWGCV2WHX6RHYGLK/events.json","paper":"https://pith.science/paper/FS5WDJ7Z"},"agent_actions":{"view_html":"https://pith.science/pith/FS5WDJ7ZDHRWGCV2WHX6RHYGLK","download_json":"https://pith.science/pith/FS5WDJ7ZDHRWGCV2WHX6RHYGLK.json","view_paper":"https://pith.science/paper/FS5WDJ7Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.07066&json=true","fetch_graph":"https://pith.science/api/pith-number/FS5WDJ7ZDHRWGCV2WHX6RHYGLK/graph.json","fetch_events":"https://pith.science/api/pith-number/FS5WDJ7ZDHRWGCV2WHX6RHYGLK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FS5WDJ7ZDHRWGCV2WHX6RHYGLK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FS5WDJ7ZDHRWGCV2WHX6RHYGLK/action/storage_attestation","attest_author":"https://pith.science/pith/FS5WDJ7ZDHRWGCV2WHX6RHYGLK/action/author_attestation","sign_citation":"https://pith.science/pith/FS5WDJ7ZDHRWGCV2WHX6RHYGLK/action/citation_signature","submit_replication":"https://pith.science/pith/FS5WDJ7ZDHRWGCV2WHX6RHYGLK/action/replication_record"}},"created_at":"2026-07-05T11:20:50.698405+00:00","updated_at":"2026-07-05T11:20:50.698405+00:00"}