{"id":"W4385958000","doi":"10.32604/jcs.2023.042501","title":"Comparative Analysis of Machine Learning Models for PDF Malware Detection: Evaluating Different Training and Testing Criteria","year":2023,"lang":"en","type":"article","venue":"Journal of Cyber Security","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Malware; Support vector machine; Naive Bayes classifier; Random forest; Machine learning; Exploit; Artificial intelligence; Scripting language; Data mining; Computer security; Operating system","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001181737,0.0001488332,0.0006003592,0.000658075,0.0001971116,0.00007644934,0.0002578808,0.00005503169,0.000008587837],"category_scores_gemma":[0.0004895999,0.0001323767,0.0001813941,0.001317073,0.00003990287,0.0006553924,0.0001407217,0.0003194996,3.341564e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005501509,"about_ca_system_score_gemma":0.00003474258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001094523,"about_ca_topic_score_gemma":0.00003410236,"domain_scores_codex":[0.9984246,0.0001817686,0.0006185913,0.0002216063,0.0003518843,0.0002015393],"domain_scores_gemma":[0.9974727,0.000833132,0.0007971019,0.0001497107,0.0006626374,0.00008474186],"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":[0.0004322948,0.0003232072,0.006785289,0.0004887154,0.003396546,0.000065951,0.0930299,0.2919495,0.1761749,0.002913911,0.0001094057,0.4243303],"study_design_scores_gemma":[0.0003154505,0.0005663823,0.003047541,0.00006817956,0.0001818462,0.0000380599,0.0004179903,0.9582287,0.02117058,0.01580132,0.00003927707,0.0001246967],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4151977,0.00009179395,0.5843369,0.00004154557,0.00008703928,0.0000981745,0.000004419113,0.0000785615,0.00006390391],"genre_scores_gemma":[0.9373456,0.00001516348,0.06253676,0.000014955,0.00005184243,0.00001115526,0.000001576446,0.000006799506,0.00001616769],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6662791,"threshold_uncertainty_score":0.5398165,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1281578408210884,"score_gpt":0.3764114026187327,"score_spread":0.2482535617976443,"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."}}