{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HIDOFSXOGONIVY2T7WTANBH7GC","short_pith_number":"pith:HIDOFSXO","schema_version":"1.0","canonical_sha256":"3a06e2caee339a8ae353fda60684ff30a6756432c2ea8e8113424290b55b47a4","source":{"kind":"arxiv","id":"2303.01819","version":1},"attestation_state":"computed","paper":{"title":"Exploring Machine Learning Privacy/Utility trade-off from a hyperparameters Lens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.CV"],"primary_cat":"cs.LG","authors_text":"Amira Guesmi, Ayoub Arous, Ihsen Alouani, Muhammad Abdullah Hanif, Muhammad Shafique","submitted_at":"2023-03-03T09:59:42Z","abstract_excerpt":"Machine Learning (ML) architectures have been applied to several applications that involve sensitive data, where a guarantee of users' data privacy is required. Differentially Private Stochastic Gradient Descent (DPSGD) is the state-of-the-art method to train privacy-preserving models. However, DPSGD comes at a considerable accuracy loss leading to sub-optimal privacy/utility trade-offs. Towards investigating new ground for better privacy-utility trade-off, this work questions; (i) if models' hyperparameters have any inherent impact on ML models' privacy-preserving properties, and (ii) if mode"},"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":"2303.01819","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-03T09:59:42Z","cross_cats_sorted":["cs.CR","cs.CV"],"title_canon_sha256":"e9a1b1d423dd03196525470606f3656e9778eaf208b999185e677c60d725f734","abstract_canon_sha256":"88fef7c8ada405532a1cc46db6e86bfb2485042778e1bd20025038a0da7c6cee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:49.572059Z","signature_b64":"ME519AMzt56B5cAErSvVn6ovPpfH62O3yRdaTeWHYQz1illcnq2kxRrn0fWwwRHZ3jGZGcrrFvc+2vB9QskvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a06e2caee339a8ae353fda60684ff30a6756432c2ea8e8113424290b55b47a4","last_reissued_at":"2026-07-05T05:47:49.571589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:49.571589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Machine Learning Privacy/Utility trade-off from a hyperparameters Lens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.CV"],"primary_cat":"cs.LG","authors_text":"Amira Guesmi, Ayoub Arous, Ihsen Alouani, Muhammad Abdullah Hanif, Muhammad Shafique","submitted_at":"2023-03-03T09:59:42Z","abstract_excerpt":"Machine Learning (ML) architectures have been applied to several applications that involve sensitive data, where a guarantee of users' data privacy is required. Differentially Private Stochastic Gradient Descent (DPSGD) is the state-of-the-art method to train privacy-preserving models. However, DPSGD comes at a considerable accuracy loss leading to sub-optimal privacy/utility trade-offs. Towards investigating new ground for better privacy-utility trade-off, this work questions; (i) if models' hyperparameters have any inherent impact on ML models' privacy-preserving properties, and (ii) if mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.01819","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/2303.01819/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":"2303.01819","created_at":"2026-07-05T05:47:49.571652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.01819v1","created_at":"2026-07-05T05:47:49.571652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.01819","created_at":"2026-07-05T05:47:49.571652+00:00"},{"alias_kind":"pith_short_12","alias_value":"HIDOFSXOGONI","created_at":"2026-07-05T05:47:49.571652+00:00"},{"alias_kind":"pith_short_16","alias_value":"HIDOFSXOGONIVY2T","created_at":"2026-07-05T05:47:49.571652+00:00"},{"alias_kind":"pith_short_8","alias_value":"HIDOFSXO","created_at":"2026-07-05T05:47:49.571652+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/HIDOFSXOGONIVY2T7WTANBH7GC","json":"https://pith.science/pith/HIDOFSXOGONIVY2T7WTANBH7GC.json","graph_json":"https://pith.science/api/pith-number/HIDOFSXOGONIVY2T7WTANBH7GC/graph.json","events_json":"https://pith.science/api/pith-number/HIDOFSXOGONIVY2T7WTANBH7GC/events.json","paper":"https://pith.science/paper/HIDOFSXO"},"agent_actions":{"view_html":"https://pith.science/pith/HIDOFSXOGONIVY2T7WTANBH7GC","download_json":"https://pith.science/pith/HIDOFSXOGONIVY2T7WTANBH7GC.json","view_paper":"https://pith.science/paper/HIDOFSXO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.01819&json=true","fetch_graph":"https://pith.science/api/pith-number/HIDOFSXOGONIVY2T7WTANBH7GC/graph.json","fetch_events":"https://pith.science/api/pith-number/HIDOFSXOGONIVY2T7WTANBH7GC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HIDOFSXOGONIVY2T7WTANBH7GC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HIDOFSXOGONIVY2T7WTANBH7GC/action/storage_attestation","attest_author":"https://pith.science/pith/HIDOFSXOGONIVY2T7WTANBH7GC/action/author_attestation","sign_citation":"https://pith.science/pith/HIDOFSXOGONIVY2T7WTANBH7GC/action/citation_signature","submit_replication":"https://pith.science/pith/HIDOFSXOGONIVY2T7WTANBH7GC/action/replication_record"}},"created_at":"2026-07-05T05:47:49.571652+00:00","updated_at":"2026-07-05T05:47:49.571652+00:00"}