{"id":"W4414704986","doi":"10.3390/s25196026","title":"ConvNet-Generated Adversarial Perturbations for Evaluating 3D Object Detection Robustness","year":2025,"lang":"en","type":"article","venue":"Sensors","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria; University of British Columbia, Okanagan Campus","funders":"British Columbia Knowledge Development Fund; Natural Sciences and Engineering Research Council of Canada","keywords":"Robustness (evolution); Object detection; Convolutional neural network; Adversarial system; Inference; Novelty detection; Pattern recognition (psychology); Deep learning; Detector","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0007176283,0.0002044428,0.0002291393,0.0002546219,0.0006530822,0.000173165,0.0004963054,0.0001454489,0.00001612374],"category_scores_gemma":[0.001673192,0.0002103083,0.0001099251,0.0008399988,0.00005196147,0.0002936477,0.0001616163,0.0002615789,0.00000988957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001690366,"about_ca_system_score_gemma":0.0002228424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006857842,"about_ca_topic_score_gemma":0.000042268,"domain_scores_codex":[0.998193,0.0002823128,0.0003366047,0.0005560425,0.0002672611,0.0003648382],"domain_scores_gemma":[0.9983346,0.000635521,0.0001539797,0.0004667,0.0003531979,0.00005594457],"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":[0.0000464728,0.00002003154,0.00006450174,0.0000223453,0.0000485096,0.000002012772,0.0003725023,0.9428384,0.005609307,0.004741345,0.0001245742,0.04611003],"study_design_scores_gemma":[0.001098092,0.00008074852,0.0003240847,0.00002731924,0.00004296619,0.000004395044,0.0001025512,0.9915891,0.004738172,0.0005557464,0.001221099,0.0002157357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1221018,0.00003317024,0.8726633,0.0005145866,0.002606736,0.0004952354,0.000003158066,0.0003627011,0.001219379],"genre_scores_gemma":[0.8453833,0.000002210782,0.1517585,0.0001807681,0.0002886401,0.00007003827,0.00001596532,0.00002001119,0.002280563],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7232815,"threshold_uncertainty_score":0.8576123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02296424581799517,"score_gpt":0.3109414592425884,"score_spread":0.2879772134245932,"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."}}