{"id":"W4392910034","doi":"10.1109/icassp48485.2024.10447992","title":"VIC-KD: Variance-Invariance-Covariance Knowledge Distillation to Make Keyword Spotting More Robust Against Adversarial Attacks","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Adversarial system; Covariance; Distillation; Variance (accounting); Computer science; Spotting; Artificial intelligence; Mathematics; Statistics; Chemistry; Chromatography","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":[0.001494405,0.001341617,0.001293033,0.0008963498,0.0005602754,0.00100537,0.002169624,0.001430939,0.00337263],"category_scores_gemma":[0.007006412,0.0004542281,0.0009447721,0.0008571967,0.001563451,0.002818029,0.003116055,0.002839611,0.001752327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008437181,"about_ca_system_score_gemma":0.001656848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00318327,"about_ca_topic_score_gemma":0.00529229,"domain_scores_codex":[0.9986035,0.000352376,0.0000852658,0.0004061183,0.0004265875,0.0001262363],"domain_scores_gemma":[0.9980717,0.0008686754,0.0001541773,0.0005680108,0.0002452173,0.00009218636],"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":[0.0004293851,0.0002301805,0.0009308018,0.0002730966,0.000145528,0.0002238941,0.000204647,0.4532078,0.01986068,0.03937173,0.01815767,0.4669646],"study_design_scores_gemma":[0.0000185242,0.00005145022,0.00008562987,0.00001088992,0.000008477002,0.00006322916,0.00001610752,0.9765391,0.006899593,0.01391419,0.002374083,0.00001864732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01031329,0.0005219526,0.9823807,0.0003327949,0.0001258491,0.00006283435,0.0003153626,0.004418652,0.00152852],"genre_scores_gemma":[0.5078733,0.0005713484,0.4743969,0.00123957,0.0002377986,0.000248496,0.003068602,0.001153356,0.01121061],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00337263,"threshold_uncertainty_score":0.01128262,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02042862100012554,"score_gpt":0.305732944577786,"score_spread":0.2853043235776605,"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."}}