{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JIEHZILFI5AELID72DRICDO4NG","short_pith_number":"pith:JIEHZILF","schema_version":"1.0","canonical_sha256":"4a087ca165474045a07fd0e2810ddc69ab5f12dc8940f630cb8b0911f4ab2f43","source":{"kind":"arxiv","id":"2403.10307","version":5},"attestation_state":"computed","paper":{"title":"Chernoff Information as a Privacy Constraint for Adversarial Classification and Membership Advantage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.IT"],"primary_cat":"cs.IT","authors_text":"Ay\\c{s}e \\\"Unsal","submitted_at":"2024-03-15T13:47:44Z","abstract_excerpt":"This work investigates a privacy metric based on Chernoff information motivated by its importance in characterizing the optimal classifier's performance. Adversarial classification centers on minimizing the probability of error when deciding between two classes in the binary setting. Classical hypothesis testing treats false alarm and mis-detection probabilities separately, resulting in asymmetric optimal error exponents. Here, we instead characterize the relationship between $\\varepsilon-$differential privacy (DP), the optimal error exponent of one error probability conditioned on the other, "},"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":"2403.10307","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2024-03-15T13:47:44Z","cross_cats_sorted":["math.IT"],"title_canon_sha256":"96eae2c148035aa8076d8eec3bd8f540e15a5a1ac43e809d94b09f17c72c6a4b","abstract_canon_sha256":"61059f92ac67150316e1c4728cc3f0d30dcb81ed0dc07180b9e257e3cad45c2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:02.156184Z","signature_b64":"xFoh0xit2Tiqh4p12hHRbaaHtlVic7stryo5Gc9WKFO98EmR27z4OR6rUe48ry7o94VmOFH0dEslZOhHVawNAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a087ca165474045a07fd0e2810ddc69ab5f12dc8940f630cb8b0911f4ab2f43","last_reissued_at":"2026-05-21T01:05:02.155180Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:02.155180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chernoff Information as a Privacy Constraint for Adversarial Classification and Membership Advantage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.IT"],"primary_cat":"cs.IT","authors_text":"Ay\\c{s}e \\\"Unsal","submitted_at":"2024-03-15T13:47:44Z","abstract_excerpt":"This work investigates a privacy metric based on Chernoff information motivated by its importance in characterizing the optimal classifier's performance. Adversarial classification centers on minimizing the probability of error when deciding between two classes in the binary setting. Classical hypothesis testing treats false alarm and mis-detection probabilities separately, resulting in asymmetric optimal error exponents. Here, we instead characterize the relationship between $\\varepsilon-$differential privacy (DP), the optimal error exponent of one error probability conditioned on the other, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10307","kind":"arxiv","version":5},"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/2403.10307/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":"2403.10307","created_at":"2026-05-21T01:05:02.155340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10307v5","created_at":"2026-05-21T01:05:02.155340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10307","created_at":"2026-05-21T01:05:02.155340+00:00"},{"alias_kind":"pith_short_12","alias_value":"JIEHZILFI5AE","created_at":"2026-05-21T01:05:02.155340+00:00"},{"alias_kind":"pith_short_16","alias_value":"JIEHZILFI5AELID7","created_at":"2026-05-21T01:05:02.155340+00:00"},{"alias_kind":"pith_short_8","alias_value":"JIEHZILF","created_at":"2026-05-21T01:05:02.155340+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/JIEHZILFI5AELID72DRICDO4NG","json":"https://pith.science/pith/JIEHZILFI5AELID72DRICDO4NG.json","graph_json":"https://pith.science/api/pith-number/JIEHZILFI5AELID72DRICDO4NG/graph.json","events_json":"https://pith.science/api/pith-number/JIEHZILFI5AELID72DRICDO4NG/events.json","paper":"https://pith.science/paper/JIEHZILF"},"agent_actions":{"view_html":"https://pith.science/pith/JIEHZILFI5AELID72DRICDO4NG","download_json":"https://pith.science/pith/JIEHZILFI5AELID72DRICDO4NG.json","view_paper":"https://pith.science/paper/JIEHZILF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10307&json=true","fetch_graph":"https://pith.science/api/pith-number/JIEHZILFI5AELID72DRICDO4NG/graph.json","fetch_events":"https://pith.science/api/pith-number/JIEHZILFI5AELID72DRICDO4NG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JIEHZILFI5AELID72DRICDO4NG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JIEHZILFI5AELID72DRICDO4NG/action/storage_attestation","attest_author":"https://pith.science/pith/JIEHZILFI5AELID72DRICDO4NG/action/author_attestation","sign_citation":"https://pith.science/pith/JIEHZILFI5AELID72DRICDO4NG/action/citation_signature","submit_replication":"https://pith.science/pith/JIEHZILFI5AELID72DRICDO4NG/action/replication_record"}},"created_at":"2026-05-21T01:05:02.155340+00:00","updated_at":"2026-05-21T01:05:02.155340+00:00"}