{"id":"W4311530262","doi":"10.3390/electronics11234007","title":"Privacy-Enhanced Federated Learning: A Restrictively Self-Sampled and Data-Perturbed Local Differential Privacy Method","year":2022,"lang":"en","type":"article","venue":"Electronics","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Natural Science Foundation of China","keywords":"Differential privacy; Computer science; MNIST database; Randomness; Information privacy; Variance (accounting); Federated learning; Data mining; Sampling (signal processing); Machine learning; Artificial intelligence; Deep learning; Computer security; Detector","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00451269,0.0006380736,0.001453349,0.0007181112,0.0007724712,0.001494094,0.003383602,0.001397418,0.001184534],"category_scores_gemma":[0.01013065,0.0003921784,0.001091173,0.001334406,0.001583635,0.003577094,0.003138471,0.002082476,0.0003425678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001297888,"about_ca_system_score_gemma":0.001701182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001161694,"about_ca_topic_score_gemma":0.0008946647,"domain_scores_codex":[0.9958663,0.001624242,0.000188955,0.000888656,0.001088024,0.0003438104],"domain_scores_gemma":[0.995425,0.001768415,0.0003578374,0.001704089,0.0005627314,0.0001818784],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005729997,0.0003725637,0.003411809,0.0001481713,0.0002033434,0.0003645697,0.0004061759,0.6063029,0.01031115,0.08889683,0.004569652,0.2844399],"study_design_scores_gemma":[0.00001595566,0.00004193018,0.0001256078,0.000005332832,0.00001161072,0.00008855564,0.00001563786,0.9741829,0.002303875,0.02256736,0.000630988,0.00001033085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00840256,0.0001035349,0.9904598,0.000135321,0.00001516496,0.00003215643,0.0000339707,0.000354206,0.0004632762],"genre_scores_gemma":[0.7857139,0.0002006425,0.2105767,0.0003510899,0.00006804112,0.0001679298,0.0002154555,0.0001067382,0.002599573],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00451269,"threshold_uncertainty_score":0.02386564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02881571519851812,"score_gpt":0.2996972271321057,"score_spread":0.2708815119335876,"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."}}