{"id":"W4323349011","doi":"10.56553/popets-2023-0055","title":"A Unified Framework for Quantifying Privacy Risk in Synthetic Data","year":2023,"lang":"en","type":"article","venue":"Proceedings on Privacy Enhancing Technologies","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute","funders":"","keywords":"Computer science; Differential privacy; Information privacy; Data anonymization; Data mining; Inference; Privacy software; Set (abstract data type); Information sensitivity; Computer security; Synthetic data; Privacy protection; Data science; Algorithm; Artificial intelligence","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":[0.02934176,0.001789088,0.001290802,0.004858113,0.001380445,0.005847834,0.00270044,0.002790115,0.001688531],"category_scores_gemma":[0.1123238,0.0007085523,0.001942169,0.003547113,0.005072232,0.008577501,0.005715961,0.005364321,0.000342197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002749261,"about_ca_system_score_gemma":0.002805541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001647808,"about_ca_topic_score_gemma":0.001212374,"domain_scores_codex":[0.9649097,0.01990526,0.002008163,0.003347185,0.008996687,0.0008331028],"domain_scores_gemma":[0.8834928,0.07417215,0.01317111,0.02115942,0.006823119,0.001181468],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001991924,0.0002163639,0.0104346,0.0003623119,0.0002686921,0.0002699155,0.0006614412,0.6204944,0.005178181,0.3102673,0.003210992,0.04843653],"study_design_scores_gemma":[0.0000246359,0.0001928111,0.002244136,0.0001384305,0.00005249015,0.0004598823,0.0002188119,0.798993,0.00381472,0.1878839,0.005881204,0.00009597519],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01541525,0.0003785731,0.979951,0.0007544415,0.00005591201,0.000275416,0.0007862008,0.0004462073,0.001937014],"genre_scores_gemma":[0.5144287,0.0007912181,0.4794139,0.000605269,0.0001828228,0.00113253,0.002172305,0.0002478768,0.001025383],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02934176,"threshold_uncertainty_score":0.1551759,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1012695659724597,"score_gpt":0.3424893920809355,"score_spread":0.2412198261084758,"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."}}