{"id":"W4310379539","doi":"10.3390/electronics11233958","title":"Vertically Federated Learning with Correlated Differential Privacy","year":2022,"lang":"en","type":"article","venue":"Electronics","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Natural Science Foundation of China","keywords":"Differential privacy; Computer science; Federated learning; Information privacy; Machine learning; Artificial intelligence; Data mining; Feature (linguistics); Computation; Privacy protection; Algorithm; Computer security","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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0002106181,0.0001759475,0.0001716763,0.0001072442,0.0007314034,0.000216068,0.01341846,0.00006495112,0.00012746],"category_scores_gemma":[0.001729847,0.0001644886,0.00003496824,0.0008684432,0.00005241231,0.0002884672,0.04602247,0.001412784,0.000026985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003443069,"about_ca_system_score_gemma":0.0002937515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005289083,"about_ca_topic_score_gemma":0.000005823372,"domain_scores_codex":[0.9979303,0.0001610948,0.0001936003,0.0005359834,0.0005012036,0.0006778355],"domain_scores_gemma":[0.9969514,0.00009877986,0.00009438524,0.002743055,0.00005329339,0.00005908612],"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":[0.001229194,0.002414216,0.0129208,0.00008558018,0.001332436,0.00114254,0.001269805,0.009855804,0.06748419,0.1611318,0.3658785,0.3752551],"study_design_scores_gemma":[0.001235985,0.001759883,0.0007282303,0.00001168318,0.00002252592,0.0001826094,0.00003422921,0.8841887,0.006262204,0.02867831,0.07633993,0.0005557717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4170021,0.0008142198,0.5671732,0.01121087,0.0002775106,0.000250901,0.000003143163,0.002615448,0.0006526715],"genre_scores_gemma":[0.9806328,0.00006302933,0.01882112,0.0001405314,0.00001398118,0.00004756772,0.0000389865,0.00002552384,0.0002164198],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8743328,"threshold_uncertainty_score":0.9919194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0109914678042454,"score_gpt":0.2280187534861931,"score_spread":0.2170272856819477,"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."}}