{"id":"W4416273494","doi":"10.1016/j.eswa.2025.130167","title":"Preserving data and model privacy during inference and training","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor; Research and Productivity Council; University of Victoria","funders":"National Research Council Canada; Alliance de recherche numérique du Canada; National Research Council","keywords":"Inference; Homomorphic encryption; Federated learning; Differential privacy; Information privacy; Table (database); Software deployment; Training (meteorology); Encryption","routes":{"ca_aff":true,"ca_fund":true,"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":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0002320087,0.0001548745,0.000188578,0.000144645,0.0003487033,0.0003635622,0.01405968,0.00007703165,4.348982e-7],"category_scores_gemma":[0.001263528,0.000135782,0.00000646512,0.0004567869,0.0001135585,0.0009879634,0.05625817,0.0001588661,0.000001500488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003297197,"about_ca_system_score_gemma":0.0001076653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008660394,"about_ca_topic_score_gemma":0.00001151702,"domain_scores_codex":[0.9985004,0.00002854592,0.0002406295,0.0008088928,0.0001658229,0.0002557095],"domain_scores_gemma":[0.9898944,0.0001794412,0.00009355647,0.009709857,0.00005542386,0.00006728365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005363383,0.0004114118,0.02409804,0.002519036,0.000604109,0.00002834109,0.01491512,0.002640583,0.02883028,0.6315657,0.1338293,0.1605044],"study_design_scores_gemma":[0.0002318908,0.000007286997,0.0005718616,0.0001973406,0.000004965677,0.00002115955,0.0002873874,0.9775715,0.0001914195,0.01522754,0.005508041,0.0001795989],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0067039,0.002277303,0.9818615,0.0068839,0.0000320713,0.0006530597,0.00002813716,0.0006331174,0.0009269699],"genre_scores_gemma":[0.684621,0.0001846415,0.3143045,0.00005391325,0.00002002375,0.0006807213,0.00001406036,0.000009144343,0.0001119924],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9749309,"threshold_uncertainty_score":0.9912747,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05999986806079979,"score_gpt":0.321658714042964,"score_spread":0.2616588459821642,"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."}}