{"id":"W2801958627","doi":"10.2196/medinform.8805","title":"Secure Logistic Regression Based on Homomorphic Encryption: Design and Evaluation","year":2018,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Cryptography and Data Security","field":"Computer Science","cited_by":247,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of General Medical Sciences; National Institute of Biomedical Imaging and Bioengineering; National Human Genome Research Institute; National Research Foundation of Korea; National Research Foundation","keywords":"Homomorphic encryption; Computer science; Encryption; Logistic regression; Machine learning; Cloud computing; Discriminative model; Support vector machine; Computation; Data mining; Artificial intelligence; Outsourcing; Classifier (UML); Algorithm; Computer security","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001578264,0.000130943,0.0001318922,0.0001418054,0.0001900051,0.0001272619,0.0004705136,0.0001726161,0.0001987481],"category_scores_gemma":[0.000291482,0.00009467638,0.00003211098,0.0003966504,0.0002744684,0.0005082685,0.0001350234,0.0002439902,0.0001049474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000250184,"about_ca_system_score_gemma":0.0001932519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001477745,"about_ca_topic_score_gemma":0.000001098432,"domain_scores_codex":[0.997924,0.0001475895,0.0003362378,0.0001430946,0.001246623,0.0002024828],"domain_scores_gemma":[0.998702,0.0002668625,0.0001350033,0.0004866763,0.0001664546,0.0002430055],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002272788,0.0007340004,0.0004868955,0.0004835666,0.00004040034,0.00004240918,0.0192977,0.0002759455,0.000048278,0.2561085,0.09616396,0.6260911],"study_design_scores_gemma":[0.0006806469,0.0004091094,0.0007113006,0.0001866493,0.00000783454,0.00001707297,0.0000750308,0.9853123,0.00007701844,0.009444594,0.002947939,0.000130441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01336133,0.00003139083,0.9841853,0.0006870196,0.0002707239,0.0003976868,0.000003465664,0.0001680787,0.000895042],"genre_scores_gemma":[0.877753,0.00002465083,0.1194472,0.002513952,0.0001691632,0.00005887715,0.00002602613,0.000005852524,0.000001386723],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9850364,"threshold_uncertainty_score":0.386079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05255794342517325,"score_gpt":0.3334524473528274,"score_spread":0.2808945039276542,"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."}}