{"id":"W4315784658","doi":"10.56553/popets-2023-0010","title":"Individualized PATE: Differentially Private Machine Learning with Individual Privacy Guarantees","year":2023,"lang":"en","type":"article","venue":"Proceedings on Privacy Enhancing Technologies","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"Bundesministerium für Bildung und Forschung","keywords":"Differential privacy; Computer science; Information privacy; Private information retrieval; MNIST database; Machine learning; Privacy by Design; Process (computing); Information sensitivity; Privacy protection; Data mining; Artificial intelligence; Computer security; Internet privacy; Deep 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":[0.00963777,0.0009961658,0.002039411,0.0006875111,0.001151838,0.002822418,0.003610442,0.002217054,0.002165872],"category_scores_gemma":[0.03407904,0.0007434831,0.001393161,0.001518478,0.002583939,0.006691891,0.008330029,0.005258714,0.0008394548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001529033,"about_ca_system_score_gemma":0.002340751,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000802792,"about_ca_topic_score_gemma":0.001151717,"domain_scores_codex":[0.9897961,0.004822019,0.0004162116,0.001845306,0.002419763,0.0007006272],"domain_scores_gemma":[0.9767599,0.009905215,0.001284804,0.01043203,0.001036258,0.0005818068],"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":[0.0007626956,0.0003954955,0.006474182,0.0002134631,0.0002303243,0.0004076667,0.0008799523,0.4435114,0.005558408,0.2662273,0.008657591,0.2666815],"study_design_scores_gemma":[0.00004502912,0.000121021,0.0005209708,0.0000220939,0.00002354067,0.0002102125,0.00004836995,0.8210919,0.003430689,0.1712572,0.003204071,0.0000247885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01035122,0.0001688782,0.9870496,0.000545905,0.00002675968,0.00005763451,0.0001512441,0.000582904,0.001065918],"genre_scores_gemma":[0.6715687,0.0003440824,0.3222447,0.0006847706,0.0001944598,0.000357629,0.0005836984,0.0002540601,0.003767961],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00963777,"threshold_uncertainty_score":0.05097002,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02652680026550532,"score_gpt":0.2602872961785198,"score_spread":0.2337604959130145,"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."}}