{"id":"W3025658176","doi":"10.48550/arxiv.2005.05750","title":"Evaluating Ensemble Robustness Against Adversarial Attacks","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Adversarial system; Transferability; Robustness (evolution); Computer science; Measure (data warehouse); Artificial intelligence; Deep neural networks; Ensemble learning; Ensemble forecasting; Machine learning; Artificial neural network; Data mining","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","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0008398539,0.0007282172,0.0007913781,0.0003280475,0.0004951759,0.0003133367,0.00455765,0.0006394897,0.00005474493],"category_scores_gemma":[0.0005792157,0.0009119059,0.000471752,0.001141582,0.0002086388,0.0008292303,0.008097252,0.002305355,0.0001874016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005364843,"about_ca_system_score_gemma":0.0007814641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009929057,"about_ca_topic_score_gemma":0.00001763577,"domain_scores_codex":[0.9950343,0.0007320232,0.0004871608,0.002568871,0.0003878825,0.0007897146],"domain_scores_gemma":[0.9960791,0.0003880918,0.0007369899,0.002050397,0.0003366882,0.0004087024],"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":[0.00006846542,0.00004795995,0.0003732327,0.0001137281,0.0001339818,0.0006541035,0.0004737053,0.9557528,0.0001384521,0.03875899,0.0003142765,0.003170275],"study_design_scores_gemma":[0.001220714,0.00008524553,0.0001378696,0.0001666891,0.0001279194,0.000005290939,0.0001372202,0.9854205,0.00008369082,0.01138331,0.0003088241,0.0009227319],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1082139,0.00004653488,0.8826434,0.0005155501,0.002634932,0.0005029922,0.00000953118,0.000881817,0.004551338],"genre_scores_gemma":[0.954194,0.00005109136,0.04401652,0.0002877272,0.0006835908,0.000002492457,0.00005093337,0.00006798779,0.0006456344],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8459801,"threshold_uncertainty_score":0.9999964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.153122486827989,"score_gpt":0.2652537893861667,"score_spread":0.1121313025581777,"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."}}