{"id":"W4378533280","doi":"10.1007/s11227-023-05378-x","title":"Local differentially private federated learning with homomorphic encryption","year":2023,"lang":"en","type":"article","venue":"The Journal of Supercomputing","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"National Natural Science Foundation of China","keywords":"Homomorphic encryption; Computer science; Differential privacy; Shuffling; MNIST database; Inference; Encryption; Reduction (mathematics); Federated learning; Data mining; Machine learning; Artificial intelligence; Theoretical computer science; Computer security; Deep learning","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":[0.002929044,0.0004715329,0.001534747,0.0006342481,0.0009895863,0.002541685,0.001935817,0.001569401,0.003751471],"category_scores_gemma":[0.007841037,0.0003771515,0.0007347748,0.001174981,0.00176425,0.005298436,0.004660621,0.00229033,0.001275652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001485614,"about_ca_system_score_gemma":0.002296938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003758096,"about_ca_topic_score_gemma":0.0003862478,"domain_scores_codex":[0.9964832,0.001121716,0.0002076538,0.0006217699,0.0009691752,0.0005964279],"domain_scores_gemma":[0.9926872,0.002347194,0.0004381929,0.0038124,0.0004850983,0.0002298735],"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":[0.002157958,0.0008455249,0.002645883,0.000316059,0.000182986,0.0004519474,0.000445211,0.2403412,0.01030425,0.4795212,0.009791531,0.2529962],"study_design_scores_gemma":[0.0001503869,0.0001900847,0.0003112622,0.00004051922,0.00003960767,0.0003848722,0.00006336136,0.6035224,0.01160589,0.3811017,0.002549227,0.00004067944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05258972,0.0003829256,0.9391714,0.0007948959,0.00009232098,0.00009680305,0.0003080543,0.001297777,0.00526601],"genre_scores_gemma":[0.9288862,0.0001413044,0.06528351,0.0002436648,0.00008552812,0.0001005627,0.0002097521,0.00005627363,0.0049932],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003751471,"threshold_uncertainty_score":0.01549047,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0252148229056052,"score_gpt":0.2452658358440073,"score_spread":0.2200510129384021,"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."}}