{"id":"W4390521467","doi":"10.20517/jsss.2023.28","title":"Privacy preserving vertical distributed learning for health data","year":2024,"lang":"en","type":"article","venue":"Journal of Surveillance Security and Safety","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor; University of Manitoba","funders":"","keywords":"Computer science; Differential privacy; Machine learning; Distributed learning; Process (computing); Information privacy; Data mining; Artificial intelligence; Stochastic gradient descent; Locality; Raw data; Partition (number theory); Artificial neural network; Computer security","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","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.003931368,0.0001445818,0.0003720954,0.0001108512,0.0002201404,0.0003500158,0.01205513,0.00009740019,0.00000494828],"category_scores_gemma":[0.02146914,0.0001212795,0.00006890985,0.0003873571,0.00008403735,0.001463239,0.02913094,0.0006986147,0.000001436818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009395949,"about_ca_system_score_gemma":0.0002589278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001427206,"about_ca_topic_score_gemma":0.00001573962,"domain_scores_codex":[0.9980296,0.0001941268,0.0006215895,0.0004237722,0.0003547861,0.0003761283],"domain_scores_gemma":[0.9957386,0.001091281,0.0001652665,0.002727615,0.0001349044,0.0001423843],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005046921,0.000279599,0.02380082,0.002292027,0.0005276147,0.0002506856,0.001887349,0.0002003587,0.0002428232,0.01789341,0.7258629,0.2262577],"study_design_scores_gemma":[0.0005977897,0.000333786,0.01045437,0.0003650617,0.00000750991,0.0002501587,0.00007083373,0.6777496,0.00005501028,0.09983657,0.2100415,0.0002377595],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01263581,0.00847576,0.851639,0.1258049,0.0007034185,0.0001824375,0.0002458295,0.0002732432,0.00003960156],"genre_scores_gemma":[0.93988,0.003804162,0.05586707,0.000150064,0.0001970071,0.000001810373,0.00008161164,0.0000137092,0.000004592956],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9272442,"threshold_uncertainty_score":0.9932901,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.040138955535509,"score_gpt":0.3243635530212524,"score_spread":0.2842245974857434,"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."}}