{"id":"W4287634898","doi":"10.48550/arxiv.2010.12112","title":"Investigating Membership Inference Attacks under Data Dependencies","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; University of Waterloo; Royal Bank of Canada","keywords":"Inference; Set (abstract data type); Computer science; Independent and identically distributed random variables; Training set; Point (geometry); Statistical inference; Data set; Data mining; Training (meteorology); Machine learning; Artificial intelligence; Computer security; Mathematics; Statistics; Random variable","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01623201,0.0008788209,0.001324363,0.001051964,0.001634573,0.00216165,0.002128606,0.002467255,0.001297596],"category_scores_gemma":[0.09276719,0.0006137944,0.0008566007,0.001237323,0.003173764,0.007585177,0.004408261,0.004725576,0.0003326306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002699405,"about_ca_system_score_gemma":0.002257789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001328284,"about_ca_topic_score_gemma":0.001086677,"domain_scores_codex":[0.9811148,0.009842428,0.0007018849,0.002051384,0.004940094,0.001349495],"domain_scores_gemma":[0.8411553,0.1307651,0.00597765,0.01825807,0.00272019,0.001123748],"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":[0.002346987,0.000836238,0.03033562,0.0004602189,0.00035927,0.0006994693,0.001110256,0.6991917,0.01603033,0.1285728,0.00787773,0.1121793],"study_design_scores_gemma":[0.00005825494,0.000176051,0.001607622,0.0000316045,0.00002865409,0.000320287,0.0001313646,0.9384319,0.008634189,0.04931837,0.001238236,0.00002340222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6183538,0.001740023,0.3653805,0.00482595,0.0001494794,0.0002537582,0.0007878805,0.001411838,0.007096678],"genre_scores_gemma":[0.9652384,0.0002526233,0.03308931,0.0003287584,0.0000597554,0.00007076436,0.0003038657,0.00007149173,0.0005851554],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01623201,"threshold_uncertainty_score":0.0858441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3590337647047022,"score_gpt":0.2705977017316751,"score_spread":0.08843606297302709,"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."}}