{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008473694,0.0002525644,0.0003928877,0.0001762134,0.0004699372,0.0001431352,0.001731339,0.0001087361,0.000003861956],"category_scores_gemma":[0.01088296,0.0001966516,0.000130613,0.002283999,0.00008973246,0.00038751,0.00041623,0.01235206,0.000007284856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000375673,"about_ca_system_score_gemma":0.001897212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003915296,"about_ca_topic_score_gemma":0.0001571416,"domain_scores_codex":[0.9944269,0.001647183,0.0006275281,0.0004474737,0.001034125,0.001816809],"domain_scores_gemma":[0.9957156,0.003128046,0.0006023998,0.0002534045,0.0001955471,0.0001049747],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001488768,0.0001259265,0.07774842,0.00003865299,0.00009765119,0.00006898231,0.0110222,0.4429571,0.00662482,0.243552,0.000006891219,0.2176085],"study_design_scores_gemma":[0.001070564,0.0008883622,0.002512343,0.0000641721,0.00003083283,0.0001234268,0.0008157509,0.9589472,0.00003827458,0.03525127,0.00003732572,0.0002204591],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.51459,0.0002284526,0.4719999,0.008897474,0.0002770042,0.0003264823,6.273094e-7,0.0002135608,0.003466576],"genre_scores_gemma":[0.9699939,0.00001477622,0.02862209,0.0003121231,0.001002899,0.000004000582,0.000001107024,0.00002573857,0.00002333926],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5159901,"threshold_uncertainty_score":0.9974488,"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."}}