{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008248994,0.00038632,0.0006010297,0.0006997751,0.0005175031,0.0006040649,0.0006989913,0.0001167461,0.00001783743],"category_scores_gemma":[0.0001055206,0.0004066098,0.0001736356,0.001542957,0.0001236023,0.00185012,0.0004464515,0.0004227018,0.000005164372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004744927,"about_ca_system_score_gemma":0.0003665402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003986469,"about_ca_topic_score_gemma":0.0001661093,"domain_scores_codex":[0.9971568,0.0001988898,0.0007905692,0.0008890835,0.0003499015,0.0006147792],"domain_scores_gemma":[0.9989941,0.000363773,0.00018546,0.0002856352,0.0000388207,0.0001321715],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008099292,0.0002521861,0.0002790705,0.00009883473,0.00007369268,0.000001441907,0.006262029,0.3332213,0.0000195898,0.6563235,0.0001807661,0.003206558],"study_design_scores_gemma":[0.002320627,0.0001348018,0.00003251669,0.0001743815,0.00004874028,5.663989e-7,0.007533982,0.9812081,0.0002915702,0.0072693,0.0005824267,0.0004029181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009503126,0.0001189124,0.989885,0.00111247,0.000578761,0.0005747989,0.00002097015,0.0001158798,0.006642884],"genre_scores_gemma":[0.9846581,0.0001203242,0.01313024,0.000258997,0.00007368074,0.00004666323,0.00008400445,0.00001709826,0.001610911],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9837078,"threshold_uncertainty_score":0.9998386,"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."}}