{"id":"W3040741943","doi":"10.1109/isncc49221.2020.9297344","title":"Evaluation of Adversarial Training on Different Types of Neural Networks in Deep Learning-based IDSs","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Adversarial system; Computer science; Artificial intelligence; Deep learning; Robustness (evolution); Convolutional neural network; Machine learning; Deep neural networks; Benchmark (surveying); Artificial neural network; Intrusion detection system; Focus (optics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006477041,0.001814888,0.001024386,0.0008462592,0.0004804999,0.000830659,0.001589612,0.001848554,0.001046398],"category_scores_gemma":[0.01547175,0.0003620725,0.0007341302,0.0004740902,0.001567848,0.002466751,0.001563911,0.001760018,0.0002764266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001545039,"about_ca_system_score_gemma":0.0007782184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002662205,"about_ca_topic_score_gemma":0.001959482,"domain_scores_codex":[0.997483,0.001114752,0.0001999644,0.0004277943,0.0004983325,0.0002761742],"domain_scores_gemma":[0.9906379,0.006261367,0.0007246406,0.001136286,0.0008713842,0.0003684467],"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":[0.0008356957,0.0003619211,0.002906582,0.0002007077,0.0001593736,0.00006737647,0.00003580608,0.9559505,0.002261059,0.002414786,0.001231297,0.03357494],"study_design_scores_gemma":[0.00002462786,0.0003357937,0.0005189948,0.00001810549,0.00002407484,0.00003528067,0.00001551563,0.9941304,0.003817886,0.0008631554,0.0002077226,0.000008315634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8225365,0.004767308,0.1573745,0.001696375,0.0005890835,0.000327589,0.0004952247,0.002483115,0.009730248],"genre_scores_gemma":[0.9789953,0.0004302898,0.01904371,0.0002194746,0.00003824087,0.00005108874,0.0003603179,0.00005051049,0.0008111005],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006477041,"threshold_uncertainty_score":0.03425431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06360988534417131,"score_gpt":0.3129073735759489,"score_spread":0.2492974882317776,"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."}}