{"id":"W4386215192","doi":"10.1109/csf57540.2023.00013","title":"Investigating Membership Inference Attacks under Data Dependencies","year":2023,"lang":"en","type":"article","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inference; Set (abstract data type); Computer science; Point (geometry); Training set; Independent and identically distributed random variables; Data set; Artificial intelligence; Statistical inference; Machine learning; Data mining; Mathematics; Random variable; Statistics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001035438,0.0001686759,0.0001531766,0.0001973929,0.0001830109,0.0003887532,0.07366978,0.000127393,0.00006708744],"category_scores_gemma":[0.0461499,0.0001509504,0.00002086608,0.001656045,0.0001804241,0.002173205,0.3092318,0.0003236637,0.0007532245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004111306,"about_ca_system_score_gemma":0.0001521333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001458078,"about_ca_topic_score_gemma":0.0001803356,"domain_scores_codex":[0.997803,0.00006904617,0.0002585523,0.0008471955,0.0005055203,0.0005167227],"domain_scores_gemma":[0.9782851,0.0008251375,0.00009268369,0.02063247,0.00006230342,0.0001023517],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[3.934139e-7,0.00001560649,0.009972163,0.00003421021,0.0000302209,0.00002533674,0.0001221308,0.0001117114,0.0009546936,0.105303,0.8667386,0.01669192],"study_design_scores_gemma":[0.00007937352,0.00001135835,0.002919135,0.00002758137,0.000002671384,0.000006514674,0.0001618842,0.4613586,0.002021162,0.5320217,0.001180533,0.0002095227],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03715586,0.0000939131,0.8100343,0.1200749,0.0008026125,0.0002756679,0.00005369136,0.01384836,0.01766063],"genre_scores_gemma":[0.5238575,0.00003859157,0.4747611,0.0008309403,0.00003370846,0.00001166601,0.00008304685,0.00001358231,0.0003698976],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8655581,"threshold_uncertainty_score":0.9681428,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2459337739695255,"score_gpt":0.3704274655717256,"score_spread":0.1244936916022001,"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."}}