{"id":"W3034631124","doi":"10.48550/arxiv.2008.02883","title":"Stronger and Faster Wasserstein Adversarial Attacks","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Wasserstein metric; Oracle; Adversarial system; Residual; Minification; Metric (unit); Robustness (evolution); Mathematics; Mathematical optimization; Computer science; Algorithm; Artificial intelligence; Applied mathematics","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":[0.003115204,0.002437598,0.001960137,0.0006483259,0.0006182224,0.001357299,0.002179095,0.002233664,0.00396031],"category_scores_gemma":[0.01139978,0.0007419367,0.001368885,0.0005318624,0.002239774,0.005444958,0.00576889,0.006905905,0.001432333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001288895,"about_ca_system_score_gemma":0.001162114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001495838,"about_ca_topic_score_gemma":0.002115781,"domain_scores_codex":[0.9966261,0.0009526192,0.00016439,0.0006866067,0.001221044,0.0003491773],"domain_scores_gemma":[0.9949533,0.00251248,0.0004158565,0.001644491,0.0002893562,0.0001843708],"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":[0.0002758903,0.0001958808,0.0006650855,0.0001464763,0.0001238046,0.0001530037,0.0001340216,0.757533,0.01633061,0.1088683,0.009221297,0.1063526],"study_design_scores_gemma":[0.00001871383,0.00004614805,0.00007311474,0.00001180498,0.000008464172,0.00004958604,0.000008442083,0.9676023,0.00338818,0.02744357,0.001337898,0.00001186939],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01719552,0.0003934612,0.9744346,0.0009388581,0.0001551112,0.00009383635,0.000105525,0.002474411,0.004208741],"genre_scores_gemma":[0.6038164,0.0006279418,0.3827201,0.001476199,0.0002482806,0.0002826191,0.0005942591,0.0008573579,0.009376801],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00396031,"threshold_uncertainty_score":0.01647496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05949320945209478,"score_gpt":0.1810070433334783,"score_spread":0.1215138338813835,"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."}}