{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BIZ5CTBWNQ4JIWBLK26CYLZIM3","short_pith_number":"pith:BIZ5CTBW","schema_version":"1.0","canonical_sha256":"0a33d14c366c3894582b56bc2c2f2866d87335b879c763e4949555eee33f2b85","source":{"kind":"arxiv","id":"2312.14712","version":3},"attestation_state":"computed","paper":{"title":"Balancing Privacy, Robustness, and Efficiency in Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DC"],"primary_cat":"cs.LG","authors_text":"John Stephan, Rachid Guerraoui, Youssef Allouah","submitted_at":"2023-12-22T14:10:07Z","abstract_excerpt":"This position paper argues that achieving robustness, privacy, and efficiency simultaneously in machine learning systems is infeasible under prevailing threat models. The tension between these goals arises not from algorithmic shortcomings but from structural limitations imposed by worst-case adversarial assumptions. We advocate for a systematic research agenda aimed at formalizing the robustness-privacy-efficiency trilemma, exploring how principled relaxations of threat models can unlock better trade-offs, and designing benchmarks that expose rather than obscure the compromises made. By shift"},"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":"2312.14712","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-22T14:10:07Z","cross_cats_sorted":["cs.CR","cs.DC"],"title_canon_sha256":"6c67cf49ce4da86235fed4faab2d93eba5e54c9c24305f291c4351275b6c8144","abstract_canon_sha256":"e754815454b1c25daa97b7ccf5b3813a85910cf7f797e6f0323b17858609c0af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:17.836910Z","signature_b64":"LMBMUYp/fwwpQ5IpPmJwxgfRBRbJUJ8cfShqL8mFocNVhihojoRlhQTmVuuiyC6rMCPMhMbx8vf76bVpAEpVAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a33d14c366c3894582b56bc2c2f2866d87335b879c763e4949555eee33f2b85","last_reissued_at":"2026-07-05T11:27:17.836495Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:17.836495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Balancing Privacy, Robustness, and Efficiency in Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DC"],"primary_cat":"cs.LG","authors_text":"John Stephan, Rachid Guerraoui, Youssef Allouah","submitted_at":"2023-12-22T14:10:07Z","abstract_excerpt":"This position paper argues that achieving robustness, privacy, and efficiency simultaneously in machine learning systems is infeasible under prevailing threat models. The tension between these goals arises not from algorithmic shortcomings but from structural limitations imposed by worst-case adversarial assumptions. We advocate for a systematic research agenda aimed at formalizing the robustness-privacy-efficiency trilemma, exploring how principled relaxations of threat models can unlock better trade-offs, and designing benchmarks that expose rather than obscure the compromises made. By shift"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14712","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2312.14712/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":"2312.14712","created_at":"2026-07-05T11:27:17.836551+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.14712v3","created_at":"2026-07-05T11:27:17.836551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14712","created_at":"2026-07-05T11:27:17.836551+00:00"},{"alias_kind":"pith_short_12","alias_value":"BIZ5CTBWNQ4J","created_at":"2026-07-05T11:27:17.836551+00:00"},{"alias_kind":"pith_short_16","alias_value":"BIZ5CTBWNQ4JIWBL","created_at":"2026-07-05T11:27:17.836551+00:00"},{"alias_kind":"pith_short_8","alias_value":"BIZ5CTBW","created_at":"2026-07-05T11:27:17.836551+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28123","citing_title":"Dangerous Liaisons of Convex Learning and Non-Affine Aggregation","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BIZ5CTBWNQ4JIWBLK26CYLZIM3","json":"https://pith.science/pith/BIZ5CTBWNQ4JIWBLK26CYLZIM3.json","graph_json":"https://pith.science/api/pith-number/BIZ5CTBWNQ4JIWBLK26CYLZIM3/graph.json","events_json":"https://pith.science/api/pith-number/BIZ5CTBWNQ4JIWBLK26CYLZIM3/events.json","paper":"https://pith.science/paper/BIZ5CTBW"},"agent_actions":{"view_html":"https://pith.science/pith/BIZ5CTBWNQ4JIWBLK26CYLZIM3","download_json":"https://pith.science/pith/BIZ5CTBWNQ4JIWBLK26CYLZIM3.json","view_paper":"https://pith.science/paper/BIZ5CTBW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.14712&json=true","fetch_graph":"https://pith.science/api/pith-number/BIZ5CTBWNQ4JIWBLK26CYLZIM3/graph.json","fetch_events":"https://pith.science/api/pith-number/BIZ5CTBWNQ4JIWBLK26CYLZIM3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BIZ5CTBWNQ4JIWBLK26CYLZIM3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BIZ5CTBWNQ4JIWBLK26CYLZIM3/action/storage_attestation","attest_author":"https://pith.science/pith/BIZ5CTBWNQ4JIWBLK26CYLZIM3/action/author_attestation","sign_citation":"https://pith.science/pith/BIZ5CTBWNQ4JIWBLK26CYLZIM3/action/citation_signature","submit_replication":"https://pith.science/pith/BIZ5CTBWNQ4JIWBLK26CYLZIM3/action/replication_record"}},"created_at":"2026-07-05T11:27:17.836551+00:00","updated_at":"2026-07-05T11:27:17.836551+00:00"}