{"id":"W3048313003","doi":"10.1109/tnsm.2020.3014929","title":"Multi-Stage Optimized Machine Learning Framework for Network Intrusion Detection","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Network and Service Management","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":274,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Intrusion detection system; Computer science; Oversampling; Artificial intelligence; Machine learning; Constant false alarm rate; Feature selection; Sample size determination; Network security; Data mining; Feature (linguistics); Dependency (UML); Mathematics; Statistics; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004063375,0.0003177591,0.0003100917,0.00008869976,0.001180199,0.0002481508,0.0004246495,0.0001820367,0.00005629639],"category_scores_gemma":[0.000004503285,0.0003228312,0.000142295,0.001150628,0.00002264806,0.0003366814,0.00003442359,0.0006065512,0.00003116142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004691692,"about_ca_system_score_gemma":0.000009906377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003377056,"about_ca_topic_score_gemma":0.0001548895,"domain_scores_codex":[0.9978928,0.0001715825,0.0003953548,0.0007373461,0.0002654399,0.0005374656],"domain_scores_gemma":[0.9989798,0.0002028876,0.0001599621,0.0003531676,0.00007526625,0.0002288863],"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":[0.0003394719,0.00006422237,0.000002588959,0.0001212731,0.00009042952,0.000005043875,0.0004989277,0.8154268,0.00003581773,0.001742263,0.00008598628,0.1815872],"study_design_scores_gemma":[0.001274928,0.0004163387,0.00003163327,0.00009306413,0.00006650282,0.000002934199,0.00006204227,0.9516521,0.0002759757,0.0008469165,0.04494527,0.0003323287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007831404,0.0001958002,0.9930505,0.002868827,0.001435532,0.0009165007,0.000003985237,0.0005457539,0.0001999807],"genre_scores_gemma":[0.4287957,0.003042356,0.5548112,0.01171468,0.0009179281,0.0003429289,0.00001021383,0.00006684497,0.0002981535],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4382393,"threshold_uncertainty_score":0.9999224,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02953981615032476,"score_gpt":0.2499424353563529,"score_spread":0.2204026192060281,"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."}}