{"id":"W4312076523","doi":"10.1007/978-3-031-26409-2_18","title":"MEAD: A Multi-Armed Approach for Evaluation of Adversarial Examples Detectors","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure; McGill University","funders":"","keywords":"Computer science; Adversarial system; Detector; Metric (unit); Artificial intelligence; Machine learning; Computer security; Data mining; Telecommunications","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":[0.006960776,0.002307676,0.001920455,0.002341771,0.0007744894,0.002028771,0.003858438,0.004573532,0.008959327],"category_scores_gemma":[0.01387102,0.001234291,0.001405673,0.001095899,0.001043448,0.002245964,0.003449235,0.00251785,0.002160158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001056363,"about_ca_system_score_gemma":0.001285005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002718966,"about_ca_topic_score_gemma":0.004650923,"domain_scores_codex":[0.9963607,0.001797094,0.0001943678,0.0005085232,0.000915196,0.0002242055],"domain_scores_gemma":[0.9951574,0.003018436,0.0002139745,0.0006204597,0.0008229857,0.000166711],"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":[0.0009870157,0.0002505922,0.001372299,0.0003277708,0.0004670663,0.0001439864,0.00009459841,0.5755744,0.007714341,0.01605034,0.01776184,0.3792558],"study_design_scores_gemma":[0.00002371601,0.00005777036,0.00008308276,0.00001163708,0.00001002861,0.0000277938,0.000007075179,0.9936009,0.001895555,0.003418543,0.0008534946,0.0000103998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006244453,0.0003120531,0.9862726,0.0001195259,0.00007449873,0.0001444641,0.0002213012,0.004809578,0.001801579],"genre_scores_gemma":[0.1109952,0.000137883,0.8830902,0.0002270076,0.00005274378,0.000357989,0.0008095969,0.0007077766,0.003621641],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008959327,"threshold_uncertainty_score":0.03681254,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07078720065733597,"score_gpt":0.3125172800365263,"score_spread":0.2417300793791904,"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."}}