{"id":"W2950088694","doi":"10.48550/arxiv.1807.02905","title":"Vulnerability Analysis of Chest X-Ray Image Classification Against Adversarial Attacks","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Pooling; Adversarial system; Deep learning; Computer science; Artificial intelligence; Vulnerability (computing); Task (project management); Image (mathematics); Pattern recognition (psychology); Contextual image classification; Machine learning; Computer security; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002319925,0.0007032707,0.0005007447,0.0009295417,0.0002834561,0.000496408,0.0005476633,0.0008272238,0.0007657756],"category_scores_gemma":[0.01096931,0.0002258877,0.0005274528,0.0003409736,0.001056398,0.001011279,0.001183756,0.001135381,0.0001989662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008852606,"about_ca_system_score_gemma":0.0003710682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001330036,"about_ca_topic_score_gemma":0.0008504721,"domain_scores_codex":[0.9985616,0.0005268403,0.00008064262,0.0002168627,0.0004380495,0.0001760611],"domain_scores_gemma":[0.9933645,0.004379421,0.0007125956,0.0008437498,0.0005111899,0.000188556],"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":[0.0008278426,0.0001163249,0.01366658,0.000169055,0.0002553903,0.0004078833,0.0001348052,0.8838604,0.02185969,0.00566152,0.003076809,0.06996368],"study_design_scores_gemma":[0.000005478093,0.00008671348,0.00308278,0.00001548895,0.00002162549,0.0001287895,0.00001803522,0.9842827,0.01009429,0.001931964,0.0003202369,0.00001200976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7914459,0.001712671,0.1999176,0.001511045,0.0001647036,0.000108894,0.000437008,0.001247739,0.003454444],"genre_scores_gemma":[0.9884424,0.0002035296,0.01045367,0.0000967119,0.00002405139,0.00001881012,0.0001803377,0.0000345052,0.0005458912],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002319925,"threshold_uncertainty_score":0.01226914,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0740751252021232,"score_gpt":0.2411806684136449,"score_spread":0.1671055432115217,"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."}}