{"id":"W4392412869","doi":"10.1109/swc57546.2023.10449008","title":"A Deep Learning-based Data Usability Enhancement Scheme for Differential Privacy","year":2023,"lang":"en","type":"article","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"National Natural Science Foundation of China; University of Guelph","keywords":"Usability; Computer science; Differential privacy; Scheme (mathematics); Information privacy; Human–computer interaction; Internet privacy; Data mining; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00309215,0.0006434062,0.000921478,0.0008114842,0.0006348278,0.001226096,0.001666844,0.0009647709,0.001530462],"category_scores_gemma":[0.01059231,0.0003125109,0.0008431652,0.00120103,0.001366442,0.003774239,0.003365693,0.00215941,0.0003939467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001081155,"about_ca_system_score_gemma":0.001244527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000650761,"about_ca_topic_score_gemma":0.0007208679,"domain_scores_codex":[0.9959162,0.001130279,0.0003038301,0.0006970676,0.001618045,0.0003345619],"domain_scores_gemma":[0.9943801,0.001668677,0.0005538468,0.001980812,0.001191338,0.0002253813],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000995767,0.0005307572,0.004386605,0.0004280396,0.0002372061,0.000514993,0.0006291193,0.09598557,0.1143153,0.1012876,0.007724818,0.6729642],"study_design_scores_gemma":[0.00006576985,0.000420729,0.001378152,0.00004132531,0.00009501591,0.0007342138,0.00009834048,0.8742015,0.07110666,0.04528446,0.006495928,0.00007787285],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01733035,0.000185385,0.9806463,0.0002163051,0.00004256246,0.00009016988,0.00007468391,0.0003645918,0.001049696],"genre_scores_gemma":[0.7458045,0.0003735664,0.2486841,0.0004156584,0.00009501785,0.0002088674,0.0002845351,0.00007612586,0.004057535],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00309215,"threshold_uncertainty_score":0.01635307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.079157283687772,"score_gpt":0.3301185963397775,"score_spread":0.2509613126520055,"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."}}