{"id":"W3181858657","doi":"10.1007/978-3-030-81242-3_2","title":"Comparing Local and Central Differential Privacy Using Membership Inference Attacks","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Differential privacy; Inference; Computer science; Upper and lower bounds; Differential (mechanical device); Data mining; Artificial intelligence; Mathematics","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":[0.0125599,0.0007233032,0.002037764,0.001068865,0.001500259,0.004862913,0.003247201,0.00236317,0.004170286],"category_scores_gemma":[0.04735349,0.000702482,0.001076535,0.002232109,0.004311391,0.01123592,0.007536291,0.004171364,0.000640093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002906869,"about_ca_system_score_gemma":0.001860694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004726113,"about_ca_topic_score_gemma":0.000523571,"domain_scores_codex":[0.981734,0.008774432,0.0004499764,0.001729742,0.005409554,0.001902215],"domain_scores_gemma":[0.932404,0.04613362,0.002042923,0.01591516,0.002650386,0.0008538143],"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":[0.004333205,0.0004327435,0.005431432,0.0002743037,0.0002900851,0.000247263,0.0007301889,0.1965279,0.008812168,0.6216031,0.005144363,0.1561732],"study_design_scores_gemma":[0.0001072668,0.0003718947,0.00127023,0.00004311601,0.0001324205,0.0003079425,0.0002424039,0.6923433,0.01140151,0.2906483,0.003075314,0.00005633575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1781212,0.001259351,0.7990656,0.001426059,0.0001983318,0.000127494,0.0002320246,0.0007759191,0.01879386],"genre_scores_gemma":[0.9609478,0.0002519577,0.03555518,0.0001487306,0.0001235459,0.00006153548,0.0001187522,0.0001277837,0.002664842],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0125599,"threshold_uncertainty_score":0.06642395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06331319455675687,"score_gpt":0.2916578776809519,"score_spread":0.228344683124195,"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."}}