{"id":"W4406946785","doi":"10.1109/lgrs.2025.3536005","title":"SHAP-Assisted Resilience Enhancement Against Adversarial Perturbations in Optical and SAR Image Classification","year":2025,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Adversarial system; Resilience (materials science); Computer science; Image (mathematics); Contextual image classification; Remote sensing; Optical imaging; Synthetic aperture radar; Artificial intelligence; Computer vision; Pattern recognition (psychology); Geology; Optics; Physics","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":[],"consensus_categories":[],"category_scores_codex":[0.0005961191,0.0001737189,0.0001855619,0.0003154168,0.0004482036,0.0002964881,0.0003608865,0.0000771386,5.074776e-7],"category_scores_gemma":[0.000308753,0.0001655295,0.000030449,0.0008481601,0.0005327706,0.0006136774,0.0001978966,0.0003076507,0.000003002795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000127391,"about_ca_system_score_gemma":0.000103154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001696583,"about_ca_topic_score_gemma":0.00002317854,"domain_scores_codex":[0.9981298,0.0001274269,0.0003037158,0.0007443089,0.0003056965,0.0003889784],"domain_scores_gemma":[0.9991651,0.0002276664,0.00009942493,0.0003683801,0.00005541742,0.00008400952],"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":[0.00001598746,0.00001953778,0.0001666639,0.00002241529,0.000005742817,0.00004414582,0.0009634881,0.001013502,0.4184544,0.00107988,0.0001649194,0.5780492],"study_design_scores_gemma":[0.0004235725,0.00002066235,0.02918344,0.0001533524,0.000007597985,0.00001627166,0.0001645285,0.9680143,0.001159092,0.000298944,0.00035365,0.0002045782],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3090756,0.00001819925,0.6784663,0.01109296,0.0005777868,0.0001303477,2.80522e-7,0.00004834203,0.0005901507],"genre_scores_gemma":[0.6600073,0.00004079054,0.3369157,0.002829848,0.00005145517,1.911031e-7,0.000001340262,0.000004966769,0.0001484431],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9670008,"threshold_uncertainty_score":0.6750097,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01215064829716259,"score_gpt":0.2638341849958837,"score_spread":0.2516835366987211,"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."}}