{"id":"W4408529537","doi":"10.1038/s41598-025-93447-x","title":"Enhancing malware detection with feature selection and scaling techniques using machine learning models","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wycliffe College","funders":"Debreceni Egyetem","keywords":"Feature selection; Computer science; Normalization (sociology); Artificial intelligence; Preprocessor; Linear discriminant analysis; Machine learning; Malware; Boosting (machine learning); Gradient boosting; Pattern recognition (psychology); Data mining; Model selection; Principal component analysis; Data pre-processing; Feature (linguistics); Scaling; Random forest; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0009955574,0.0001978681,0.0001915653,0.000621849,0.001045203,0.0006469593,0.0001616178,0.0001211718,0.000001626077],"category_scores_gemma":[0.00008976903,0.0001805039,0.0000421726,0.001681974,0.00008926622,0.001358828,0.0002079212,0.0003785445,2.688644e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001799864,"about_ca_system_score_gemma":0.0001128932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008660474,"about_ca_topic_score_gemma":0.00021005,"domain_scores_codex":[0.9979727,0.00006990201,0.0003109882,0.001005165,0.0003427643,0.0002984366],"domain_scores_gemma":[0.9988014,0.00003036706,0.0002888953,0.0004860199,0.0003273605,0.00006596139],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001700652,0.0000250338,0.001078822,0.00009104703,0.00002072084,0.00008474012,0.000287081,0.008241114,0.8937247,0.0004198425,0.0000299142,0.09597999],"study_design_scores_gemma":[0.00003727015,0.00004012579,0.00002578944,0.0001537465,0.00001026935,0.0006500419,0.00002565759,0.2226936,0.761439,0.0132056,0.001554796,0.0001641404],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07116833,0.0001948497,0.9258259,0.0000440202,0.0007396651,0.0003249602,1.867524e-7,0.001500243,0.0002018704],"genre_scores_gemma":[0.7129087,0.000006144421,0.2863023,0.00002097318,0.00002036073,0.00002807871,0.000001845439,0.00001280097,0.000698757],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6417404,"threshold_uncertainty_score":0.8038959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009857232811341644,"score_gpt":0.2476275985927596,"score_spread":0.2377703657814179,"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."}}