{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00517885,0.0005816419,0.0007632365,0.001236011,0.0002955525,0.0002229566,0.003618623,0.0004557658,0.000009808125],"category_scores_gemma":[0.001770533,0.0005577154,0.0002566465,0.0009377037,0.0006473286,0.0005518764,0.0014558,0.0007530957,0.000007662185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000493421,"about_ca_system_score_gemma":0.001181504,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006479374,"about_ca_topic_score_gemma":0.00006405335,"domain_scores_codex":[0.9942399,0.0001622846,0.0007834115,0.001846745,0.002252991,0.0007146838],"domain_scores_gemma":[0.9954413,0.001463709,0.0006916221,0.001392769,0.0008735235,0.0001370714],"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":[0.00001479141,0.0000249963,0.00002983871,0.00006944708,0.00002459196,0.000002967825,0.0008584457,0.6294656,0.0001219754,0.004969429,0.000003909718,0.364414],"study_design_scores_gemma":[0.001496208,0.0001338068,0.000130107,0.0001652286,0.00005364734,0.00000764874,8.723691e-7,0.961208,0.0006168003,0.03557622,0.00007873745,0.0005326993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00009454603,0.0001078777,0.9946432,0.00008104522,0.002788745,0.001496338,0.00001027964,0.0002466458,0.0005314013],"genre_scores_gemma":[0.09253021,0.000009039074,0.9065316,0.00009103831,0.0005339066,0.00007638903,0.00002467485,0.00007054341,0.0001325424],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3638813,"threshold_uncertainty_score":0.9996874,"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."}}