{"id":"W4323545679","doi":"10.1016/j.asoc.2023.110173","title":"A gradient-based approach for adversarial attack on deep learning-based network intrusion detection systems","year":2023,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of New Brunswick","funders":"","keywords":"Adversarial system; Computer science; Artificial intelligence; Intrusion detection system; Deep learning; Machine learning; Transferability; Artificial neural network; Deep neural networks; Jacobian matrix and determinant; Data mining; Pattern recognition (psychology); Mathematics","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":[0.001361901,0.001070396,0.0009507713,0.0009241011,0.0003907894,0.0005743469,0.001261033,0.0007735139,0.00115566],"category_scores_gemma":[0.003270965,0.0003804809,0.0005975218,0.0004359978,0.0009793931,0.001165138,0.001467419,0.00153265,0.0002393224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001128595,"about_ca_system_score_gemma":0.0009027975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003938397,"about_ca_topic_score_gemma":0.003070816,"domain_scores_codex":[0.9993007,0.0001596293,0.00003669713,0.0001263593,0.0002798465,0.00009681287],"domain_scores_gemma":[0.9990472,0.0004124706,0.0001170737,0.0001111325,0.0002375237,0.00007459333],"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":[0.000134088,0.00007856669,0.000738913,0.00004551143,0.00004212011,0.00007973699,0.00004468704,0.8783426,0.00541187,0.008501616,0.001523601,0.1050567],"study_design_scores_gemma":[0.0000020703,0.00001311553,0.00003777095,0.000001123961,0.000001784891,0.000007275255,9.933701e-7,0.9983488,0.00051674,0.0009720672,0.00009659444,0.00000165629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03289385,0.0004336079,0.9633274,0.0003136775,0.00006058889,0.00007176263,0.00003201723,0.001256905,0.001610187],"genre_scores_gemma":[0.8629912,0.0002444988,0.1336924,0.000265242,0.00006067675,0.00009112542,0.0001152297,0.000117582,0.002421976],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003938397,"threshold_uncertainty_score":0.008188605,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02341448391837548,"score_gpt":0.2629387199650703,"score_spread":0.2395242360466949,"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."}}