{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Y7O63VBOXWPE42K5PIRM4OCTAB","short_pith_number":"pith:Y7O63VBO","schema_version":"1.0","canonical_sha256":"c7ddedd42ebd9e4e695d7a22ce38530077d6c644bc8dd86d6463c5b64cdcb451","source":{"kind":"arxiv","id":"2108.04417","version":2},"attestation_state":"computed","paper":{"title":"Privacy-Preserving Machine Learning: Methods, Challenges and Directions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"James Joshi, Nathalie Baracaldo, Runhua Xu","submitted_at":"2021-08-10T02:58:31Z","abstract_excerpt":"Machine learning (ML) is increasingly being adopted in a wide variety of application domains. Usually, a well-performing ML model relies on a large volume of training data and high-powered computational resources. Such a need for and the use of huge volumes of data raise serious privacy concerns because of the potential risks of leakage of highly privacy-sensitive information; further, the evolving regulatory environments that increasingly restrict access to and use of privacy-sensitive data add significant challenges to fully benefiting from the power of ML for data-driven applications. A tra"},"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":"2108.04417","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-10T02:58:31Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"3b97da0b1c7f54acd51c95b4d6fd799a60e9454c9f91594a9c72d62545558488","abstract_canon_sha256":"4264705e160b7dbd8a31d988921bc62c8e7e77e8aef507f1ccbfe15f46f44dfa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:16:33.743001Z","signature_b64":"wH/WodhwpzTdV1d97v4kGI+KvaABRJJv2uBYPRpCImWbuDh+Cbe7e3xkXlQjb92Sd89x99tNdou4oXFFYARcCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7ddedd42ebd9e4e695d7a22ce38530077d6c644bc8dd86d6463c5b64cdcb451","last_reissued_at":"2026-07-05T03:16:33.742489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:16:33.742489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Privacy-Preserving Machine Learning: Methods, Challenges and Directions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"James Joshi, Nathalie Baracaldo, Runhua Xu","submitted_at":"2021-08-10T02:58:31Z","abstract_excerpt":"Machine learning (ML) is increasingly being adopted in a wide variety of application domains. Usually, a well-performing ML model relies on a large volume of training data and high-powered computational resources. Such a need for and the use of huge volumes of data raise serious privacy concerns because of the potential risks of leakage of highly privacy-sensitive information; further, the evolving regulatory environments that increasingly restrict access to and use of privacy-sensitive data add significant challenges to fully benefiting from the power of ML for data-driven applications. A tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.04417","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/2108.04417/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":"2108.04417","created_at":"2026-07-05T03:16:33.742555+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.04417v2","created_at":"2026-07-05T03:16:33.742555+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.04417","created_at":"2026-07-05T03:16:33.742555+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y7O63VBOXWPE","created_at":"2026-07-05T03:16:33.742555+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y7O63VBOXWPE42K5","created_at":"2026-07-05T03:16:33.742555+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y7O63VBO","created_at":"2026-07-05T03:16:33.742555+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10361","citing_title":"Near-Exponential Convergence Rates for kNN Classification based on Boltzmann Margin","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27219","citing_title":"Nonlinear Data Integration via Kernel Methods for Data Collaboration Analysis","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2403.02780","citing_title":"Data Collaboration Analysis with Orthonormal Basis Selection and Alignment","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2503.16251","citing_title":"RESFL: An Uncertainty-Aware Framework for Responsible Federated Learning by Balancing Privacy, Fairness and Utility","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2510.26841","citing_title":"FedPF: Accurate Target Privacy Preserving Federated Learning Balancing Fairness and Utility","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18966","citing_title":"Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training","ref_index":191,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12335","citing_title":"All in One: A Unified Synthetic Data Pipeline for Multimodal Video Understanding","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05571","citing_title":"Understanding User Privacy Perceptions of GenAI Smartphones","ref_index":78,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y7O63VBOXWPE42K5PIRM4OCTAB","json":"https://pith.science/pith/Y7O63VBOXWPE42K5PIRM4OCTAB.json","graph_json":"https://pith.science/api/pith-number/Y7O63VBOXWPE42K5PIRM4OCTAB/graph.json","events_json":"https://pith.science/api/pith-number/Y7O63VBOXWPE42K5PIRM4OCTAB/events.json","paper":"https://pith.science/paper/Y7O63VBO"},"agent_actions":{"view_html":"https://pith.science/pith/Y7O63VBOXWPE42K5PIRM4OCTAB","download_json":"https://pith.science/pith/Y7O63VBOXWPE42K5PIRM4OCTAB.json","view_paper":"https://pith.science/paper/Y7O63VBO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.04417&json=true","fetch_graph":"https://pith.science/api/pith-number/Y7O63VBOXWPE42K5PIRM4OCTAB/graph.json","fetch_events":"https://pith.science/api/pith-number/Y7O63VBOXWPE42K5PIRM4OCTAB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y7O63VBOXWPE42K5PIRM4OCTAB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y7O63VBOXWPE42K5PIRM4OCTAB/action/storage_attestation","attest_author":"https://pith.science/pith/Y7O63VBOXWPE42K5PIRM4OCTAB/action/author_attestation","sign_citation":"https://pith.science/pith/Y7O63VBOXWPE42K5PIRM4OCTAB/action/citation_signature","submit_replication":"https://pith.science/pith/Y7O63VBOXWPE42K5PIRM4OCTAB/action/replication_record"}},"created_at":"2026-07-05T03:16:33.742555+00:00","updated_at":"2026-07-05T03:16:33.742555+00:00"}