{"id":"W7117482120","doi":"10.1109/dicta68720.2025.11302451","title":"Robosurg: Resilience of Vision-Language Models Against Adversarial Attacks in Robotic Surgery","year":2025,"lang":"","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Adversarial system; Robustness (evolution); Resilience (materials science); Context (archaeology); Compromise; Adversarial machine learning; Robot","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003463252,0.0007307482,0.001625781,0.001803143,0.0003052407,0.0002758461,0.002768948,0.0005266012,0.0001720102],"category_scores_gemma":[0.001993698,0.0007726867,0.0005191318,0.004831549,0.0005668196,0.002403155,0.002513313,0.001265671,0.00003589273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003981711,"about_ca_system_score_gemma":0.001812402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001303361,"about_ca_topic_score_gemma":0.0003200415,"domain_scores_codex":[0.9920707,0.001200148,0.002385447,0.001829563,0.001201038,0.001313048],"domain_scores_gemma":[0.9931022,0.003414753,0.0007716083,0.002158757,0.0003180061,0.0002346567],"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":[0.0001493834,0.0003188223,0.006020943,0.0002273552,0.00005660198,0.0001658231,0.001454726,0.905395,0.0003533037,0.02039418,0.0008043615,0.06465954],"study_design_scores_gemma":[0.001179472,0.00006562551,0.005072741,0.00145565,0.0000417911,0.000004155875,0.0004805076,0.9886977,0.0004117599,0.001900074,0.00004756627,0.0006429767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03791826,0.001200815,0.9318539,0.00133553,0.004817146,0.0006345594,0.000003340013,0.0001541453,0.0220823],"genre_scores_gemma":[0.973577,0.0002321597,0.02264047,0.0004807299,0.0001458796,0.00001430484,0.000007553374,0.00003738698,0.002864555],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9356587,"threshold_uncertainty_score":0.9994724,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0144399426512419,"score_gpt":0.2953815405494566,"score_spread":0.2809415978982147,"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."}}