{"id":"W3049178586","doi":"10.1145/3389683","title":"Deep Learning for Multi-instance Biometric Privacy","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Management Information Systems","topic":"Biometric Identification and Security","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Biometrics; Computer science; Artificial intelligence; Random projection; Convolutional neural network; Modality (human–computer interaction); Deep learning; Authentication (law); Identification (biology); Machine learning; Support vector machine; Pattern recognition (psychology); Computer security","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":[],"consensus_categories":[],"category_scores_codex":[0.0003677538,0.0001382628,0.000147822,0.001179707,0.0003485611,0.0006146691,0.001040215,0.00006146287,0.0000110292],"category_scores_gemma":[0.00008497333,0.0001406777,0.0000965935,0.003986732,0.00001487025,0.002029474,0.00002791134,0.0001310079,0.0004896928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008584357,"about_ca_system_score_gemma":0.00001168252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007739329,"about_ca_topic_score_gemma":3.954912e-7,"domain_scores_codex":[0.9985716,0.00005187847,0.00051827,0.0002346167,0.0004097786,0.0002138395],"domain_scores_gemma":[0.9988819,0.00008170222,0.0002300271,0.0005189459,0.0001706965,0.0001166733],"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":[0.00003296819,0.0001599958,0.00005910547,0.0009492428,0.0001733845,0.000001290285,0.005066067,0.03242312,0.00001860652,0.04218498,0.001172441,0.9177588],"study_design_scores_gemma":[0.000753118,0.00006253934,0.0003232238,0.00001290632,0.00001173823,0.000001187999,0.0006332039,0.6251929,0.00006940719,0.00002046252,0.3727657,0.0001535868],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00006972057,0.00006796002,0.9958875,0.001118977,0.0006507473,0.0009650842,0.000007728052,0.0004284618,0.000803859],"genre_scores_gemma":[0.8792806,0.0001442927,0.1186695,0.0009235925,0.00002810183,0.0003126731,0.00004517042,0.000009335824,0.0005867415],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9176052,"threshold_uncertainty_score":0.6294173,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06197770605970799,"score_gpt":0.2771877586914677,"score_spread":0.2152100526317597,"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."}}