{"id":"W7106634211","doi":"10.1016/j.procs.2025.10.196","title":"A Comparative Study to Feature Selection for Network Security, By using Deep Learning as an Embedded Model","year":2025,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Rimouski; HEC Montréal; Université du Québec à Montréal","funders":"Université du Québec à Rimouski","keywords":"Singular value decomposition; Benchmark (surveying); Feature selection; Deep learning; Principal component analysis; Curse of dimensionality; Feature (linguistics); Component (thermodynamics); Selection (genetic algorithm)","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":[0.002133186,0.0008397483,0.0006446394,0.001517165,0.0002504944,0.0006012056,0.0003953337,0.0004903077,0.001382925],"category_scores_gemma":[0.006262667,0.0001329349,0.0005685694,0.001448857,0.0003072763,0.00138369,0.0004504534,0.0005869575,0.0002173798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004815109,"about_ca_system_score_gemma":0.0002903775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001802646,"about_ca_topic_score_gemma":0.001526136,"domain_scores_codex":[0.9988025,0.0005503337,0.00007658857,0.0001452138,0.0003621121,0.00006327859],"domain_scores_gemma":[0.9960161,0.002821518,0.0001358687,0.0003561472,0.0006101208,0.00006017974],"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":[0.001518029,0.0005724352,0.009648344,0.0003890489,0.0004432891,0.0002059488,0.00009071308,0.1368029,0.009283148,0.00430808,0.005206015,0.831532],"study_design_scores_gemma":[0.00005770168,0.00147481,0.007479886,0.00005042857,0.0001205845,0.0002445326,0.00007949485,0.9741216,0.009575683,0.003237433,0.003531501,0.00002636998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4674391,0.01824627,0.5022774,0.001382983,0.0002810649,0.000225413,0.0003858684,0.001529878,0.008232011],"genre_scores_gemma":[0.9088886,0.003003015,0.08558708,0.00009989728,0.0001199272,0.00006781703,0.0005738025,0.00006384037,0.001595926],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002133186,"threshold_uncertainty_score":0.01128155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01988181705804715,"score_gpt":0.3185802084535893,"score_spread":0.2986983913955422,"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."}}