{"id":"W4393005048","doi":"10.3390/app14062576","title":"Adversarial Attacks on Medical Segmentation Model via Transformation of Feature Statistics","year":2024,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Ministry of Education, India; National Research Foundation of Korea; Hanyang University; Korea Institute for Advancement of Technology; Ministry of Trade, Industry and Energy; National Research Foundation","keywords":"Computer science; Segmentation; Artificial intelligence; Feature (linguistics); Adversarial system; Pattern recognition (psychology); Transformation (genetics); Statistics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008797846,0.0001151721,0.000126207,0.0001621046,0.0001887982,0.0001296056,0.0007112763,0.00009034967,0.00003022603],"category_scores_gemma":[0.00004584833,0.00009316603,0.00003235574,0.0006133584,0.0002045818,0.0004835318,0.00007292652,0.000257563,0.00002728036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004164534,"about_ca_system_score_gemma":0.000249496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008892817,"about_ca_topic_score_gemma":0.000005826299,"domain_scores_codex":[0.9980713,0.00003894507,0.0002207222,0.0003395287,0.001133803,0.0001957272],"domain_scores_gemma":[0.999439,0.0002462554,0.00006802012,0.0001498514,0.00002869307,0.00006817353],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001014694,0.00001768576,0.000006963045,0.00003641621,0.00000828706,0.000003379629,0.002606121,0.2635251,0.001324461,0.6421418,0.0006829,0.08963677],"study_design_scores_gemma":[0.0001770673,0.00006463614,0.00002123297,0.00002957957,0.000007051594,0.0000032967,0.00009267341,0.979044,0.002055323,0.0182505,0.0001518575,0.0001027992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00211238,0.00002278213,0.988497,0.00116125,0.0005478131,0.0001521902,0.000007033117,0.0001253834,0.007374158],"genre_scores_gemma":[0.8237748,0.000006857302,0.1759128,0.0001708815,0.00007277658,0.000009152282,0.000008757911,0.000004942106,0.00003910052],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8216624,"threshold_uncertainty_score":0.3799201,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01648488935171837,"score_gpt":0.303485871632201,"score_spread":0.2870009822804826,"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."}}