{"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":"codex-gemma-dda1882f352a","candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.009576232,0.0002617197,0.0005196541,0.0003345368,0.0003864947,0.000189076,0.002681781,0.000276588,0.000002362743],"category_scores_gemma":[0.0008179466,0.0001789742,0.0002780368,0.000458926,0.00006250417,0.000226022,0.0006844734,0.005157132,0.000001992406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004609533,"about_ca_system_score_gemma":0.00189625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008913627,"about_ca_topic_score_gemma":0.000281878,"domain_scores_codex":[0.9958674,0.001855479,0.0003975451,0.0005485827,0.0003014338,0.001029532],"domain_scores_gemma":[0.9968481,0.00155594,0.0003746361,0.0009962268,0.0001837536,0.0000413578],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001016293,0.003511309,0.05927254,0.0001912323,0.005791157,0.00002451013,0.001747298,0.01407541,0.00043561,0.8646402,0.0001157714,0.04917871],"study_design_scores_gemma":[0.001879071,0.004945568,0.02754388,0.0002618027,0.0005818342,0.00007723864,0.001648889,0.2806253,0.00108126,0.680535,0.0002083262,0.000611816],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4932776,0.0004363284,0.5043007,0.0006069985,0.0002009196,0.0007101197,0.00002896147,0.0003738562,0.00006448491],"genre_scores_gemma":[0.9992449,0.000128205,0.000427327,0.00003766086,0.00003529449,0.00006452009,0.00002836834,0.000008875127,0.00002487849],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5059672,"threshold_uncertainty_score":0.997138,"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."}}