{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001684429,0.0009540411,0.0005278599,0.000467677,0.0003109948,0.0007057583,0.0008073875,0.001020402,0.001216338],"category_scores_gemma":[0.006763639,0.0003231431,0.0007014548,0.0002961219,0.001953859,0.001261365,0.002041713,0.001906974,0.0003112463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009862366,"about_ca_system_score_gemma":0.0006224675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001336409,"about_ca_topic_score_gemma":0.0009529837,"domain_scores_codex":[0.9988079,0.0004977741,0.00004121221,0.0002231441,0.0003179233,0.0001120412],"domain_scores_gemma":[0.9970771,0.001789899,0.0004169876,0.0004995405,0.0001363968,0.00008005598],"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":[0.0001142749,0.00002861521,0.0009950487,0.00002852023,0.00003905383,0.0001580151,0.00006374345,0.9303037,0.007774849,0.03626149,0.001343615,0.02288907],"study_design_scores_gemma":[0.000004175856,0.00002794372,0.0001669897,0.00000527375,0.000004227543,0.00004842814,0.000005243985,0.9886242,0.002081767,0.008619261,0.0004062507,0.00000619717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04759392,0.0001649148,0.9480436,0.0005838468,0.00006006141,0.00004323356,0.00007929574,0.0005677216,0.002863368],"genre_scores_gemma":[0.938332,0.000236434,0.0580673,0.0003294887,0.00006056962,0.00008841803,0.0001342488,0.0001137122,0.002637983],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001684429,"threshold_uncertainty_score":0.008908212,"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."}}