{"id":"W4362554721","doi":"10.1007/s44248-023-00002-y","title":"Evaluating Word Embedding Feature Extraction Techniques for Host-Based Intrusion Detection Systems","year":2023,"lang":"en","type":"article","venue":"Discover Data","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Vector Institute","keywords":"Word2vec; Computer science; Intrusion detection system; Word embedding; Host (biology); Embedding; System call; Data mining; Feature (linguistics); Artificial intelligence; Feature extraction; Machine learning","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001440747,0.0001641885,0.0001594465,0.0002509416,0.0004700295,0.0005457549,0.0009279488,0.0001524854,0.000005211373],"category_scores_gemma":[0.0002735595,0.0001540941,0.00005744145,0.0009240484,0.00001969383,0.002199349,0.000541013,0.0002360617,0.00003069841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009650414,"about_ca_system_score_gemma":0.00006572146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006827978,"about_ca_topic_score_gemma":0.00004763926,"domain_scores_codex":[0.99822,0.0001298305,0.0002506519,0.0006864509,0.0004094832,0.000303562],"domain_scores_gemma":[0.9981648,0.0002476422,0.0001960003,0.001233837,0.0001025428,0.00005521309],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001460273,0.00006995533,0.00003259756,0.000199952,0.00003124988,0.000007066003,0.0002445736,0.005052324,0.1041273,0.00127053,0.02120033,0.8676181],"study_design_scores_gemma":[0.0002263463,0.0001432759,0.0001650289,0.0001281753,0.00001550403,0.000008810456,0.00006679635,0.9473455,0.0203978,0.0002918355,0.03101753,0.0001934081],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02226648,0.0001041208,0.972852,0.0005563041,0.002294406,0.0007851571,0.00009742636,0.0009690684,0.00007507142],"genre_scores_gemma":[0.9614083,0.00008113216,0.0357413,0.0002177816,0.001050775,0.0002907125,0.0008760083,0.00003952991,0.0002944554],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9422932,"threshold_uncertainty_score":0.6283774,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0767570373767207,"score_gpt":0.378191707457228,"score_spread":0.3014346700805073,"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."}}