{"id":"W4229026610","doi":"10.2478/popets-2022-0058","title":"Visualizing Privacy-Utility Trade-Offs in Differentially Private Data Releases","year":2022,"lang":"en","type":"article","venue":"Proceedings on Privacy Enhancing Technologies","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Northwestern University; National Science Foundation","keywords":"Differential privacy; Computer science; Inference; Context (archaeology); Probabilistic logic; Noise (video); Private information retrieval; Set (abstract data type); Statistical inference; Task (project management); Aggregate (composite); Data mining; Information retrieval; Computer security; Artificial intelligence; Statistics; 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":[0.01928521,0.001092633,0.0008603086,0.002273471,0.0009786558,0.00443091,0.001588538,0.002037707,0.004549838],"category_scores_gemma":[0.1178902,0.0006628522,0.0008809277,0.001470152,0.002834281,0.006212266,0.003886231,0.003595047,0.0003808948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00205235,"about_ca_system_score_gemma":0.0009884217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001801481,"about_ca_topic_score_gemma":0.001525169,"domain_scores_codex":[0.9846312,0.0105583,0.0007190256,0.001360756,0.00228717,0.0004434541],"domain_scores_gemma":[0.8109933,0.1690547,0.007582435,0.00806339,0.002853767,0.001452415],"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":[0.006585259,0.001921152,0.08995943,0.002508362,0.0004326579,0.002494568,0.04700512,0.2716863,0.04005336,0.1550894,0.01690433,0.3653601],"study_design_scores_gemma":[0.0005526376,0.001250366,0.03411246,0.0005242099,0.0001350547,0.0007693173,0.005955894,0.7012712,0.02003389,0.2173704,0.01774666,0.0002778734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6518084,0.001304349,0.3256873,0.004909552,0.00009636721,0.0004052915,0.0009906001,0.005650736,0.009147371],"genre_scores_gemma":[0.9322633,0.0001841247,0.06604715,0.0002254145,0.00002462217,0.0001747775,0.0002803756,0.0002280711,0.0005721262],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01928521,"threshold_uncertainty_score":0.1019911,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04930740550062166,"score_gpt":0.296920273391974,"score_spread":0.2476128678913524,"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."}}