{"id":"W4285037962","doi":"10.1007/978-3-031-10684-2_1","title":"Assessing Differentially Private Variational Autoencoders Under Membership Inference","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Differential privacy; Computer science; Inference; Differential (mechanical device); Artificial intelligence; Algorithm; Data mining; Machine 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":[0.01597856,0.001662556,0.00330618,0.001121903,0.001001519,0.004178189,0.004174556,0.00588701,0.003954434],"category_scores_gemma":[0.08055633,0.001779245,0.001510644,0.001157113,0.004731085,0.007407763,0.007032706,0.006076825,0.0006677817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003031519,"about_ca_system_score_gemma":0.002124944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001846586,"about_ca_topic_score_gemma":0.001710434,"domain_scores_codex":[0.9910167,0.004822789,0.0003575893,0.001311659,0.002009476,0.0004816703],"domain_scores_gemma":[0.9081334,0.08222594,0.002003846,0.004374554,0.001980598,0.001281624],"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":[0.0009750121,0.0002320745,0.004810308,0.0002625989,0.0002654684,0.0002282084,0.0002175092,0.7269627,0.002036141,0.2020672,0.00251855,0.05942419],"study_design_scores_gemma":[0.00002786356,0.00006900705,0.000313739,0.00002347963,0.00001698992,0.0000455475,0.00001953824,0.8656862,0.0009072407,0.1326377,0.000238463,0.00001430314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06613504,0.000677266,0.9281316,0.001752209,0.00009023794,0.00007201061,0.0003018973,0.000444775,0.002394951],"genre_scores_gemma":[0.8488969,0.0009054238,0.1393343,0.0006171843,0.0005874592,0.0002125524,0.001333253,0.0003133563,0.007799551],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01597856,"threshold_uncertainty_score":0.08450371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05353202494932276,"score_gpt":0.297122149988138,"score_spread":0.2435901250388152,"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."}}