{"id":"W4394825026","doi":"10.5121/ijaia.2024.15205","title":"Immunizing Image Classifiers Against Localized Adversary Attack","year":2024,"lang":"en","type":"article","venue":"International Journal of Artificial Intelligence & Applications","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Adversarial system; Convolutional neural network; Computer science; Adversary; Deep learning; Artificial intelligence; Vulnerability (computing); Machine learning; Convolution (computer science); Image (mathematics); Scale (ratio); Deep neural networks; Artificial neural network; Pattern recognition (psychology); Computer security; Geography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000781182,0.0001927643,0.0002178147,0.0005461723,0.0001711205,0.0007321886,0.00258928,0.00008998081,0.0000934263],"category_scores_gemma":[0.0002086207,0.0001845726,0.0002674046,0.0007118505,0.0001882595,0.001442507,0.0003426424,0.0006992336,0.0003353827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002828568,"about_ca_system_score_gemma":0.0003195111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001387546,"about_ca_topic_score_gemma":0.000004251425,"domain_scores_codex":[0.9975699,0.00009935822,0.0009680903,0.0003419601,0.000766673,0.0002539862],"domain_scores_gemma":[0.9979314,0.0004172833,0.000366437,0.0003854963,0.0007610265,0.0001383419],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003213672,0.0001123569,0.00001961077,0.00001330999,0.0002028911,0.0001664025,0.0009001897,0.03918642,0.01185577,0.2849899,0.0006917524,0.6618292],"study_design_scores_gemma":[0.00008968395,0.00007782637,0.00002920269,0.0002587722,0.00004538407,0.0002981072,0.001007623,0.7340447,0.01157499,0.0595521,0.1926098,0.0004118057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001301452,0.0004896724,0.9886119,0.004518027,0.002166923,0.0001985168,0.000006344869,0.0001503802,0.00255679],"genre_scores_gemma":[0.7847777,0.0003129921,0.2129179,0.0003660685,0.001385983,0.00005183748,0.00001217995,0.00003457082,0.0001407326],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7834763,"threshold_uncertainty_score":0.7526651,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03972670245325821,"score_gpt":0.356184689767243,"score_spread":0.3164579873139848,"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."}}