{"id":"W7147457981","doi":"10.1145/3769872.3769899","title":"Exploring Comparative Visual Approaches for Understanding Model Trade-offs in Adversarial Machine Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Adversarial system; Leverage (statistics); Robustness (evolution); Empirical research; Visual analytics; Visualization; Design science","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":[0.02576553,0.001719535,0.0005728665,0.00258092,0.0007679419,0.004392424,0.002057737,0.00131106,0.006793734],"category_scores_gemma":[0.07174208,0.0007656622,0.0008287852,0.0008739341,0.002621719,0.004432671,0.004020971,0.002398353,0.0005576528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00180663,"about_ca_system_score_gemma":0.001022499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007335826,"about_ca_topic_score_gemma":0.001342646,"domain_scores_codex":[0.9871631,0.009918232,0.0003607729,0.0008497185,0.001407681,0.0003004357],"domain_scores_gemma":[0.9279732,0.06014536,0.002891559,0.005121526,0.003200826,0.0006675291],"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":[0.001506286,0.000623282,0.01030844,0.001991809,0.000286178,0.0006055044,0.0125094,0.3878029,0.05259869,0.1911005,0.006208483,0.3344585],"study_design_scores_gemma":[0.0002667089,0.001318616,0.003576723,0.000624983,0.0001073082,0.0003558683,0.002771176,0.7678932,0.03052501,0.1724145,0.01998166,0.0001642887],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06335577,0.0005897732,0.9246783,0.00123618,0.00006729313,0.0004022572,0.0002015882,0.001559115,0.007909746],"genre_scores_gemma":[0.5156611,0.0002152727,0.4817476,0.0002729639,0.00003116916,0.0006213925,0.0001328781,0.0004218306,0.0008958477],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02576553,"threshold_uncertainty_score":0.1362627,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4788588060073659,"score_gpt":0.3751515109379527,"score_spread":0.1037072950694131,"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."}}