{"id":"W2004511978","doi":"10.1007/s11416-009-0122-8","title":"Unknown malcode detection and the imbalance problem","year":2009,"lang":"en","type":"article","venue":"Journal in Computer Virology","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Code (set theory); Set (abstract data type); Malware; Binary classification; Feature selection; Categorization; Class (philosophy); Signature (topology); Selection (genetic algorithm); Data mining; Artificial intelligence; Information retrieval; Computer security; Support vector machine; Programming language","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":[0.004666159,0.0007066022,0.001629382,0.005299879,0.001889722,0.00272034,0.001541336,0.002744672,0.002462588],"category_scores_gemma":[0.05246907,0.0006577571,0.0005748632,0.003419386,0.001620445,0.006255806,0.001879906,0.002134215,0.0007392058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001235349,"about_ca_system_score_gemma":0.0007597552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001831493,"about_ca_topic_score_gemma":0.001368948,"domain_scores_codex":[0.9940597,0.001388123,0.000317179,0.001454648,0.002131297,0.0006490526],"domain_scores_gemma":[0.9576331,0.02792347,0.005833267,0.004185851,0.003600564,0.0008237259],"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":[0.002178664,0.001053103,0.1857174,0.0004157117,0.0003344862,0.002665427,0.0008188008,0.1567851,0.0155181,0.06791176,0.03841527,0.5281861],"study_design_scores_gemma":[0.00007209199,0.000109543,0.02045689,0.00004938402,0.00007450374,0.00280871,0.0002967545,0.8518762,0.007979673,0.1112695,0.004949426,0.00005730592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.627219,0.002625132,0.345722,0.01023781,0.0008133821,0.0001678133,0.001999627,0.001834923,0.009380354],"genre_scores_gemma":[0.9703994,0.0004389979,0.02517442,0.0003189223,0.0008222781,0.00004580197,0.0009044387,0.0001139315,0.001781869],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005299879,"threshold_uncertainty_score":0.02467734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005380248098878364,"score_gpt":0.2360256257957565,"score_spread":0.2306453776968782,"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."}}