{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001637269,0.001270129,0.0008186721,0.001638039,0.0002379425,0.0007506537,0.0004874048,0.0006606099,0.001271784],"category_scores_gemma":[0.005969093,0.0002067343,0.0007091789,0.001145068,0.00030676,0.00187402,0.0007625092,0.0006643587,0.0008269283],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00043726,"about_ca_system_score_gemma":0.0004361616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001921993,"about_ca_topic_score_gemma":0.002067862,"domain_scores_codex":[0.9988441,0.0003218243,0.0001750296,0.0002481954,0.0002885808,0.0001221493],"domain_scores_gemma":[0.9969163,0.001929051,0.0002194983,0.0002682845,0.0005838802,0.00008300578],"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":[0.001842104,0.001037566,0.01835495,0.0006595118,0.0004650006,0.0001955973,0.0002006208,0.1150452,0.03827899,0.001102849,0.005435574,0.8173822],"study_design_scores_gemma":[0.0000893301,0.002026271,0.009892496,0.00004158476,0.0001493087,0.0003598788,0.0001932692,0.9292831,0.05487853,0.0009486548,0.002094338,0.00004325674],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8647048,0.002571647,0.1233694,0.0003119228,0.0003074479,0.0002170027,0.001495171,0.00492529,0.002097269],"genre_scores_gemma":[0.9057147,0.0006159516,0.08798498,0.00007873143,0.00006109755,0.0001165505,0.00382487,0.0001384618,0.001464675],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001921993,"threshold_uncertainty_score":0.008658767,"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."}}