{"id":"W4415366712","doi":"10.1109/tvt.2025.3623875","title":"A Vision-Based Covert Attack and Hybrid Adversary Detection for Autonomous Vehicles Using Generative Adversarial Network","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Vehicular Technology","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Ministère de la Défense Nationale; Innovation for Defence Excellence and Security","keywords":"Covert; Adversary; Adversarial system; Artificial neural network; Global Positioning System; Remotely operated underwater vehicle; Battlefield","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0007325645,0.0008412053,0.001007808,0.001496396,0.002517851,0.0002762704,0.000990139,0.001096653,0.00001976581],"category_scores_gemma":[0.00008382212,0.0009819575,0.0004589165,0.002294128,0.0008595315,0.0006150939,0.00004922209,0.001742195,0.00001175167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008270465,"about_ca_system_score_gemma":0.0008826808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000985876,"about_ca_topic_score_gemma":0.00008852695,"domain_scores_codex":[0.9951329,0.0004436761,0.0009540995,0.001913851,0.0004178029,0.001137641],"domain_scores_gemma":[0.9970252,0.0007444565,0.0004504376,0.001214589,0.0004000885,0.0001652474],"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":[0.0004968554,0.0002476182,0.00002255691,0.0001024167,0.0003898999,0.00003956312,0.00009146683,0.8446031,0.00626784,0.0005771759,0.00006599841,0.1470956],"study_design_scores_gemma":[0.00373276,0.001032897,0.00002271223,0.0003796135,0.0005413624,0.00005755531,0.00008724634,0.9183682,0.07045536,0.001538726,0.003049309,0.0007343247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06414025,0.0007362834,0.9249113,0.002399297,0.005267784,0.001768765,0.00005179398,0.0006917623,0.00003279522],"genre_scores_gemma":[0.9085906,0.00006286402,0.09007012,0.000637943,0.0002323427,0.0002009934,0.000005541236,0.00006486138,0.0001347215],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8444504,"threshold_uncertainty_score":0.9992631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01367627938155531,"score_gpt":0.2828904057170907,"score_spread":0.2692141263355354,"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."}}