{"id":"W3141811040","doi":"10.1109/tvt.2021.3069426","title":"An Adversarial Attack Based on Incremental Learning Techniques for Unmanned in 6G Scenes","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Vehicular Technology","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"National Natural Science Foundation of China","keywords":"Adversarial system; Software deployment; Computer science; Artificial intelligence; Machine learning; Forgetting; Deep learning; Artificial neural network; Deep neural networks; Incremental learning; Pascal (unit); Computer security","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":[0.0007149993,0.001063196,0.0005918784,0.0003338846,0.0004026771,0.0004539897,0.0009152501,0.0007587633,0.001397688],"category_scores_gemma":[0.002145921,0.0002110035,0.0006422712,0.0002360514,0.0009177317,0.001297561,0.001374563,0.00158721,0.000266876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00052413,"about_ca_system_score_gemma":0.0004482763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002236498,"about_ca_topic_score_gemma":0.002189155,"domain_scores_codex":[0.9993315,0.0001525003,0.0000214185,0.0001258324,0.0002328097,0.0001360006],"domain_scores_gemma":[0.9993163,0.0003223412,0.00006679666,0.0001537386,0.00009226109,0.0000485291],"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":[0.0004786564,0.0001167613,0.001832224,0.00008199208,0.0001126222,0.0007200926,0.0001444847,0.8182735,0.02348485,0.01842086,0.007684299,0.1286497],"study_design_scores_gemma":[0.000008112145,0.00007472001,0.0003068028,0.000006157567,0.000009836339,0.0001385818,0.00001347711,0.9893,0.004894044,0.004095245,0.001140604,0.00001239611],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08614953,0.000708881,0.9040579,0.0008064967,0.0002757445,0.0001087396,0.0001649439,0.001776114,0.005951687],"genre_scores_gemma":[0.9319555,0.000288775,0.06370554,0.0004289405,0.0000617702,0.00006978146,0.0002547779,0.00008804831,0.003146808],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002236498,"threshold_uncertainty_score":0.004675746,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01449079218211305,"score_gpt":0.289374839424724,"score_spread":0.274884047242611,"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."}}