{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MP4MHE5VKV5Y4W4S3RTURM5PGZ","short_pith_number":"pith:MP4MHE5V","schema_version":"1.0","canonical_sha256":"63f8c393b5557b8e5b92dc6748b3af366ec6e6a45a02d2a132915b753c56822a","source":{"kind":"arxiv","id":"1905.02383","version":3},"attestation_state":"computed","paper":{"title":"Gaussian Differential Privacy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Roth, Jinshuo Dong, Weijie J. Su","submitted_at":"2019-05-07T06:57:19Z","abstract_excerpt":"Differential privacy has seen remarkable success as a rigorous and practical formalization of data privacy in the past decade. This privacy definition and its divergence based relaxations, however, have several acknowledged weaknesses, either in handling composition of private algorithms or in analyzing important primitives like privacy amplification by subsampling. Inspired by the hypothesis testing formulation of privacy, this paper proposes a new relaxation, which we term `$f$-differential privacy' ($f$-DP). This notion of privacy has a number of appealing properties and, in particular, avo"},"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":"1905.02383","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-07T06:57:19Z","cross_cats_sorted":["cs.CR","cs.DS","stat.ML"],"title_canon_sha256":"ff494c15e8ab9f126463faa78b5f1dfc7b3fdb5127787c3024c31739f9cc0177","abstract_canon_sha256":"05efce7870d06a352bc55e9999d04b3a12343eccee0190be1a1bebfa3c812224"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:37.517141Z","signature_b64":"xZplLgiljL/6j4WbSaDrd8w1ucvYAoXER5EuNZZSRg6vIGV1mzaLdxXwJtAm+eVzniOs0NYDyKyVort/7w6fBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63f8c393b5557b8e5b92dc6748b3af366ec6e6a45a02d2a132915b753c56822a","last_reissued_at":"2026-05-17T23:44:37.516721Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:37.516721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gaussian Differential Privacy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Roth, Jinshuo Dong, Weijie J. Su","submitted_at":"2019-05-07T06:57:19Z","abstract_excerpt":"Differential privacy has seen remarkable success as a rigorous and practical formalization of data privacy in the past decade. This privacy definition and its divergence based relaxations, however, have several acknowledged weaknesses, either in handling composition of private algorithms or in analyzing important primitives like privacy amplification by subsampling. Inspired by the hypothesis testing formulation of privacy, this paper proposes a new relaxation, which we term `$f$-differential privacy' ($f$-DP). This notion of privacy has a number of appealing properties and, in particular, avo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.02383","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1905.02383","created_at":"2026-05-17T23:44:37.516788+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.02383v3","created_at":"2026-05-17T23:44:37.516788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.02383","created_at":"2026-05-17T23:44:37.516788+00:00"},{"alias_kind":"pith_short_12","alias_value":"MP4MHE5VKV5Y","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"MP4MHE5VKV5Y4W4S","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"MP4MHE5V","created_at":"2026-05-18T12:33:21.387695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"2605.21378","citing_title":"Auditing Apple's DifferentialPrivacy.framework: Implementation Bugs, Misconfigurations, and Practical Risks","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21780","citing_title":"Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21938","citing_title":"Optimal Guarantees for Auditing R\\'enyi Differentially Private Machine Learning","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21378","citing_title":"Auditing Apple's DifferentialPrivacy.framework: Implementation Bugs, Misconfigurations, and Practical Risks","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15648","citing_title":"Rethinking the Security of DP-SGD: A Corrected Analysis of Differentially Private Machine Learning","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2511.21804","citing_title":"Beyond Membership: Limitations of Add/Remove Adjacency in Differential Privacy","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2601.10237","citing_title":"Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MP4MHE5VKV5Y4W4S3RTURM5PGZ","json":"https://pith.science/pith/MP4MHE5VKV5Y4W4S3RTURM5PGZ.json","graph_json":"https://pith.science/api/pith-number/MP4MHE5VKV5Y4W4S3RTURM5PGZ/graph.json","events_json":"https://pith.science/api/pith-number/MP4MHE5VKV5Y4W4S3RTURM5PGZ/events.json","paper":"https://pith.science/paper/MP4MHE5V"},"agent_actions":{"view_html":"https://pith.science/pith/MP4MHE5VKV5Y4W4S3RTURM5PGZ","download_json":"https://pith.science/pith/MP4MHE5VKV5Y4W4S3RTURM5PGZ.json","view_paper":"https://pith.science/paper/MP4MHE5V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.02383&json=true","fetch_graph":"https://pith.science/api/pith-number/MP4MHE5VKV5Y4W4S3RTURM5PGZ/graph.json","fetch_events":"https://pith.science/api/pith-number/MP4MHE5VKV5Y4W4S3RTURM5PGZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MP4MHE5VKV5Y4W4S3RTURM5PGZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MP4MHE5VKV5Y4W4S3RTURM5PGZ/action/storage_attestation","attest_author":"https://pith.science/pith/MP4MHE5VKV5Y4W4S3RTURM5PGZ/action/author_attestation","sign_citation":"https://pith.science/pith/MP4MHE5VKV5Y4W4S3RTURM5PGZ/action/citation_signature","submit_replication":"https://pith.science/pith/MP4MHE5VKV5Y4W4S3RTURM5PGZ/action/replication_record"}},"created_at":"2026-05-17T23:44:37.516788+00:00","updated_at":"2026-05-17T23:44:37.516788+00:00"}