{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001981866,0.001070677,0.0006506559,0.0004142085,0.0005912667,0.001053358,0.001314459,0.0012329,0.002037583],"category_scores_gemma":[0.009519491,0.0004310127,0.0006769142,0.0002021269,0.001760487,0.001921039,0.003142035,0.002189662,0.0004751608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001100915,"about_ca_system_score_gemma":0.001299111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005775541,"about_ca_topic_score_gemma":0.00441655,"domain_scores_codex":[0.9986216,0.0005055261,0.0000521032,0.0002642645,0.0003581293,0.0001984447],"domain_scores_gemma":[0.9965225,0.00210455,0.00032387,0.0006872156,0.000231012,0.0001308386],"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":[0.0002134767,0.00005735124,0.001195303,0.00007076715,0.0000559439,0.0001313558,0.0001279205,0.9552196,0.005716938,0.01011154,0.002631071,0.02446884],"study_design_scores_gemma":[0.000007099665,0.00006290234,0.0001758571,0.00001057404,0.000006716036,0.00003922698,0.00002282162,0.9876074,0.002515434,0.008770982,0.000770829,0.00001014378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2018142,0.001547816,0.7784417,0.002702897,0.0002841466,0.0001606723,0.0004282081,0.007085699,0.007534837],"genre_scores_gemma":[0.9528825,0.0003223805,0.04338336,0.0004600124,0.00005088727,0.0000756639,0.0003799232,0.0003095175,0.002135616],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005775541,"threshold_uncertainty_score":0.01148385,"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."}}