{"id":"W3106679794","doi":"10.2139/ssrn.3750914","title":"Ethical Testing in the Real World: Evaluating Physical Testing of Adversarial Machine Learning","year":2020,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Adversarial system; Computer science; Machine learning; Artificial intelligence; Psychology; Engineering ethics; Engineering","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":[0.02497587,0.0007784743,0.0005026112,0.0009534491,0.000637673,0.001725599,0.001875406,0.002435789,0.005881793],"category_scores_gemma":[0.2409398,0.0002294192,0.0004712263,0.0004806345,0.005589355,0.002835761,0.003157952,0.001987014,0.0007267056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001128993,"about_ca_system_score_gemma":0.001265489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001138158,"about_ca_topic_score_gemma":0.0008568953,"domain_scores_codex":[0.9762068,0.01845755,0.0006264013,0.001089001,0.003166466,0.0004536106],"domain_scores_gemma":[0.7241746,0.2364853,0.01223275,0.01637696,0.007727202,0.003003176],"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":[0.008276388,0.003499495,0.07999549,0.001145419,0.0007824788,0.00104293,0.001606324,0.492644,0.005419486,0.1656509,0.0180836,0.2218536],"study_design_scores_gemma":[0.0009919185,0.005186962,0.02361415,0.0005713365,0.0001877235,0.001214663,0.0009368851,0.7419912,0.007249222,0.2073828,0.01053913,0.0001340076],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7629716,0.001940913,0.1944822,0.006447864,0.001100881,0.000670559,0.0005740575,0.0004549213,0.03135695],"genre_scores_gemma":[0.9851777,0.0001920611,0.01257703,0.0004764429,0.00008824945,0.000196692,0.0001788218,0.00004682505,0.001066098],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02497587,"threshold_uncertainty_score":0.1320866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04798838117388857,"score_gpt":0.3304596729115644,"score_spread":0.2824712917376758,"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."}}