{"id":"W4386952188","doi":"10.1109/tce.2023.3318509","title":"AP2FL: Auditable Privacy-Preserving Federated Learning Framework for Electronics in Healthcare","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Consumer Electronics","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":117,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brandon University; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Electronics; Computer science; Health care; Computer security; Information privacy; Internet privacy; Engineering; Electrical engineering","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":["metaepi_narrow","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001052187,0.0004466449,0.0004919443,0.0008019438,0.0008828464,0.0003583554,0.01105829,0.0005319249,0.00001840156],"category_scores_gemma":[0.003371615,0.0005129395,0.0001712121,0.003527137,0.00008486099,0.0007889391,0.0007817927,0.002634681,0.0001287173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008637129,"about_ca_system_score_gemma":0.0008688159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001099123,"about_ca_topic_score_gemma":0.0006594511,"domain_scores_codex":[0.9953535,0.0002436725,0.0006278311,0.001199464,0.0005076557,0.002067829],"domain_scores_gemma":[0.9935173,0.0014894,0.0002028447,0.00443907,0.0002007729,0.0001505568],"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":[0.0007261097,0.00143171,0.001376363,0.0011188,0.001094076,0.0001567737,0.0009940262,0.05891499,0.01082459,0.0723186,0.1021217,0.7489222],"study_design_scores_gemma":[0.001003719,0.0005753146,0.00005841505,0.0001961104,0.00002697762,0.00002145229,0.00005681175,0.6597359,0.03084558,0.2869704,0.01976482,0.0007445551],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01059273,0.001809979,0.9468545,0.03596951,0.0006609967,0.0008920973,0.00003360779,0.003146673,0.00003989221],"genre_scores_gemma":[0.8649639,0.005276668,0.1279817,0.0005156923,0.00003789522,0.0007521824,0.00004424926,0.0001282935,0.0002994712],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8543711,"threshold_uncertainty_score":0.9997322,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03265274158927208,"score_gpt":0.3048174634814943,"score_spread":0.2721647218922222,"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."}}