{"id":"W3080189561","doi":"10.1109/icpr48806.2021.9413263","title":"Adversarially Training for Audio Classifiers","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Adversarial system; Computer science; Adversary; Deep neural networks; Artificial intelligence; Benchmarking; Robustness (evolution); Machine learning; Artificial neural network; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001780026,0.0009067372,0.0006463031,0.0004122955,0.0003842349,0.0007452776,0.0009858147,0.001118863,0.002804629],"category_scores_gemma":[0.008041612,0.0003017175,0.0005705171,0.0002397111,0.001349168,0.001426043,0.001779613,0.001936325,0.0007150921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007269668,"about_ca_system_score_gemma":0.0005015107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001213876,"about_ca_topic_score_gemma":0.001238281,"domain_scores_codex":[0.9988417,0.0003279898,0.00004567986,0.0002698246,0.0003327986,0.000182012],"domain_scores_gemma":[0.9965321,0.002262318,0.000277096,0.0006033643,0.0002257835,0.00009921253],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002245774,0.00005253721,0.001234775,0.00006981741,0.00007175098,0.0001044704,0.00003868653,0.924302,0.008362823,0.01485786,0.001503675,0.04917713],"study_design_scores_gemma":[0.000005936791,0.00005192222,0.0002202167,0.00001216647,0.000009266262,0.0000499901,0.000007665075,0.9884006,0.00483724,0.005588282,0.0008095682,0.000007102441],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1146964,0.001059489,0.8721766,0.0008433656,0.0002630078,0.0001068741,0.0002480135,0.001312558,0.009293709],"genre_scores_gemma":[0.9439983,0.000289176,0.05097989,0.0002803993,0.0000700503,0.00007815198,0.0002190936,0.00009707942,0.003987826],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002804629,"threshold_uncertainty_score":0.009413838,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07006534765257547,"score_gpt":0.3117161311778678,"score_spread":0.2416507835252923,"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."}}