{"id":"W2586380145","doi":"10.1109/smc.2016.7844751","title":"Detecting BGP anomalies using machine learning techniques","year":2016,"lang":"en","type":"article","venue":"","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Support vector machine; Redundancy (engineering); Artificial intelligence; Feature selection; Machine learning; Relevance (law); Border Gateway Protocol; Data mining; Pattern recognition (psychology); Routing protocol; Computer network; Routing (electronic design automation)","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":[],"consensus_categories":[],"category_scores_codex":[0.0003191918,0.00009080565,0.00008839584,0.0001007131,0.0002706606,0.00009577072,0.0002749737,0.00005499147,0.00009187848],"category_scores_gemma":[0.00006143225,0.00005917935,0.00004152043,0.0002427969,0.00002548772,0.0006360527,0.0002370462,0.0001066876,0.00002588577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003995262,"about_ca_system_score_gemma":0.00001264378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001090932,"about_ca_topic_score_gemma":0.00004439943,"domain_scores_codex":[0.9992108,0.00006994134,0.0001492513,0.0002359156,0.0001310472,0.0002030153],"domain_scores_gemma":[0.999564,0.0000767972,0.00006857945,0.000204683,0.00004319337,0.00004274659],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000005456723,0.00001250935,0.001659905,0.00000493649,0.000006738993,0.000005353311,0.0001468643,0.00001373049,0.234733,0.009261454,0.00002696641,0.754123],"study_design_scores_gemma":[0.0001300221,0.0001549055,0.000123517,0.0000698919,0.000002873506,0.00008163983,0.00001227747,0.1251434,0.8404188,0.003721183,0.02990226,0.0002392992],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1365102,0.00007227188,0.8597258,0.0002660119,0.0001735985,0.0000576912,1.366297e-7,0.0008067166,0.002387625],"genre_scores_gemma":[0.8754257,0.0000367534,0.1237665,0.000120482,0.0001220839,0.000003122458,7.380161e-8,0.000007182836,0.0005180483],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7538838,"threshold_uncertainty_score":0.2413264,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01851658836288379,"score_gpt":0.2410714857828467,"score_spread":0.2225548974199629,"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."}}