{"id":"W4283702278","doi":"10.11591/ijai.v11.i3.pp961-968","title":"Defense against adversarial attacks on deep convolutional neural networks through nonlocal denoising","year":2022,"lang":"en","type":"article","venue":"IAES International Journal of Artificial Intelligence","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Universiti Brunei Darussalam","keywords":"MNIST database; Adversarial system; Computer science; Artificial intelligence; Convolutional neural network; Deep learning; Deep neural networks; Robustness (evolution); Machine learning; Classifier (UML); Artificial neural network; Luminance","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":[0.001320111,0.0002295606,0.0002880344,0.0003113286,0.0004528261,0.0003680073,0.002360192,0.00006922067,0.0001668928],"category_scores_gemma":[0.0003590534,0.0002263303,0.0003324735,0.000410297,0.0001688859,0.0008842678,0.0004628084,0.000894093,0.00002425891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003860621,"about_ca_system_score_gemma":0.000190104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002196194,"about_ca_topic_score_gemma":0.000005847774,"domain_scores_codex":[0.9961854,0.0004911919,0.001000358,0.0003657276,0.0015823,0.0003750736],"domain_scores_gemma":[0.9975929,0.0006480279,0.0006184825,0.000276731,0.000740027,0.0001238082],"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":[0.0007628464,0.0002534851,0.00003972562,0.000001477351,0.0001088875,0.0007677129,0.0009726267,0.7037711,0.0009313361,0.06444567,0.000461066,0.227484],"study_design_scores_gemma":[0.0002623908,0.0005491957,0.0000409744,0.0000328989,0.00001815691,0.0007180857,0.0003837389,0.967905,0.005185958,0.02156456,0.003047538,0.0002914991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01380596,0.0003149093,0.9731215,0.001565174,0.01022344,0.00008989383,0.000007656093,0.00003934996,0.000832173],"genre_scores_gemma":[0.957705,0.00003087487,0.03771086,0.002761342,0.001725394,0.000004565743,0.000007182612,0.00001823336,0.0000365906],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.943899,"threshold_uncertainty_score":0.9229482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04769861058786611,"score_gpt":0.3305586075210692,"score_spread":0.2828599969332031,"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."}}