{"id":"W4406347125","doi":"10.2139/ssrn.5096180","title":"An Empirical Study on the Effectiveness of Automated Machine Learning Tools for Cybersecurity","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Technology and Data Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria; National Research Council Canada; University of Windsor","funders":"","keywords":"Computer science; Computer security; Empirical research; Artificial intelligence; Machine learning","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":[0.01495105,0.00043049,0.0003302009,0.002194384,0.0006839441,0.001725639,0.001312138,0.001286019,0.005276121],"category_scores_gemma":[0.1444149,0.0002718712,0.0004818254,0.001757622,0.001543519,0.004466179,0.001097819,0.001570776,0.00082628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008850098,"about_ca_system_score_gemma":0.0009262746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001337941,"about_ca_topic_score_gemma":0.0009905688,"domain_scores_codex":[0.9850098,0.01083278,0.0008468238,0.0007417944,0.002169199,0.0003995187],"domain_scores_gemma":[0.5509769,0.4068395,0.01751442,0.01153483,0.01042304,0.00271135],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.006770526,0.03862726,0.6567463,0.001270705,0.0007075935,0.0004815122,0.007554714,0.01350965,0.002787883,0.006447503,0.003490139,0.2616062],"study_design_scores_gemma":[0.001636166,0.04212322,0.8168537,0.0008232846,0.0008801665,0.00122795,0.01445659,0.09155666,0.01062202,0.008432528,0.01122969,0.0001580062],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9952013,0.0002221059,0.0007929878,0.0001872159,0.0000115056,0.00008623647,0.00009873519,0.00001915968,0.00338065],"genre_scores_gemma":[0.9984875,0.0001028649,0.0007943639,0.00003957506,0.00001407493,0.00003947156,0.0001155157,0.000006600413,0.0004000635],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01495105,"threshold_uncertainty_score":0.07906967,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01827739002928972,"score_gpt":0.3319433649077085,"score_spread":0.3136659748784187,"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."}}