{"id":"W4388624363","doi":"10.1109/msec.2023.3315944","title":"Privacy-Preserving Machine Learning [Cryptography]","year":2023,"lang":"en","type":"article","venue":"IEEE Security & Privacy","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Cryptography; Differential privacy; Encryption; Information leakage; Information privacy; Computation; Leakage (economics); Computer security; Artificial intelligence; Data mining; Algorithm","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.001659746,0.0005727115,0.0005575264,0.001023125,0.0006809339,0.0006679106,0.06428578,0.0003625419,0.00009053655],"category_scores_gemma":[0.02504663,0.0005968933,0.0003038897,0.004587522,0.0002292264,0.002098443,0.1565558,0.001599993,0.0009681555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001214318,"about_ca_system_score_gemma":0.0001177399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000250984,"about_ca_topic_score_gemma":0.00002767935,"domain_scores_codex":[0.9947347,0.0003589386,0.0007127386,0.001579488,0.001102631,0.001511482],"domain_scores_gemma":[0.9828466,0.0006024371,0.000328345,0.01576226,0.0001749721,0.0002854077],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004303956,0.0003948199,0.03450242,0.0003752405,0.0003280377,0.0006630761,0.004156276,0.0002101019,0.01088445,0.01402632,0.8804103,0.05400598],"study_design_scores_gemma":[0.0007407744,0.0001381937,0.003106788,0.0001311854,0.00001894359,0.00004452913,0.0000610173,0.2924865,0.01295974,0.6000829,0.08930203,0.0009274017],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6580655,0.001555541,0.2213415,0.07945944,0.0037727,0.001342365,0.00009637904,0.0292855,0.005081058],"genre_scores_gemma":[0.8907221,0.0008756052,0.1074182,0.0003676297,0.0002294701,0.00008768176,0.00008268838,0.0000910022,0.0001256736],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7911082,"threshold_uncertainty_score":0.9998097,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02959177808758929,"score_gpt":0.2796400927008302,"score_spread":0.250048314613241,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}