{"id":"W7126082940","doi":"10.1109/icdsca67083.2025.11349773","title":"Drift Robust Evaluation of Machine Learning Intrusion Detection Methods on CSE-CIC-IDS2028 Dataset","year":2025,"lang":"","type":"article","venue":"","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Constant false alarm rate; Robustness (evolution); Intrusion detection system; Benchmark (surveying); False alarm; Replicate; Sensitivity (control systems); Random forest","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":[0.01099781,0.002695771,0.001500056,0.004002369,0.0008270584,0.001472392,0.00214349,0.001557698,0.0003820935],"category_scores_gemma":[0.01493057,0.0002800419,0.0008766994,0.00203061,0.0007360454,0.001922206,0.001310682,0.001179119,0.0005494962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002155576,"about_ca_system_score_gemma":0.001481676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01370113,"about_ca_topic_score_gemma":0.01207008,"domain_scores_codex":[0.9939413,0.001534771,0.000628621,0.001505731,0.00199501,0.0003947224],"domain_scores_gemma":[0.9938257,0.002250471,0.0006822452,0.00107069,0.001871397,0.0002995289],"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":[0.002496195,0.001905194,0.1105657,0.001109474,0.001488308,0.0004758417,0.0002952166,0.4797363,0.01153715,0.002465435,0.1127949,0.2751303],"study_design_scores_gemma":[0.0001295183,0.000777876,0.03353177,0.00008631559,0.0001329054,0.0003806331,0.000194515,0.9394675,0.01264412,0.001228839,0.0113523,0.00007372051],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9060078,0.008152199,0.03900272,0.001440934,0.001776525,0.0006797488,0.0265576,0.01097461,0.005407945],"genre_scores_gemma":[0.8610137,0.0008139891,0.0409474,0.0004124545,0.0002748124,0.0003284363,0.09397611,0.000238463,0.001994596],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01370113,"threshold_uncertainty_score":0.05816263,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04873771980412079,"score_gpt":0.3521556721523633,"score_spread":0.3034179523482425,"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."}}