{"id":"W3093369224","doi":"10.22215/etd/2017-11856","title":"Statistical Evaluation of Malware Classification Algorithms","year":2017,"lang":"en","type":"dissertation","venue":"","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Malware; Univariate; Computer science; Data mining; Data set; Variance (accounting); Malware analysis; Set (abstract data type); Multivariate analysis of variance; Machine learning; Algorithm; Artificial intelligence; Statistical classification; Feature (linguistics); Multivariate statistics; Operating system","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":[0.01223971,0.001258879,0.0008205946,0.005692693,0.000641292,0.002051912,0.001183607,0.001254739,0.001386924],"category_scores_gemma":[0.06693078,0.0002205235,0.0008591539,0.002722946,0.0009032023,0.002554419,0.0009658654,0.001322745,0.0007935752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001534034,"about_ca_system_score_gemma":0.001420969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002015804,"about_ca_topic_score_gemma":0.001925336,"domain_scores_codex":[0.9889491,0.003686034,0.000736212,0.001159716,0.005061892,0.0004070995],"domain_scores_gemma":[0.9062087,0.06749045,0.004344772,0.005948226,0.01525171,0.0007561643],"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":[0.002298438,0.001553943,0.109117,0.0006529334,0.00119361,0.0001317269,0.0001894204,0.3249732,0.01070754,0.01106043,0.01573917,0.5223827],"study_design_scores_gemma":[0.00006026947,0.001445815,0.02646111,0.00006078679,0.0001492761,0.0002027421,0.0001252105,0.9499171,0.01195561,0.006996184,0.002572823,0.00005304139],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7819276,0.007240784,0.1913374,0.001711779,0.0007853322,0.000346807,0.002448985,0.0039543,0.01024702],"genre_scores_gemma":[0.9550781,0.0007793435,0.03755666,0.0001580477,0.0003589857,0.0001204206,0.004161805,0.0002599464,0.001526742],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01223971,"threshold_uncertainty_score":0.06473053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07140947260885143,"score_gpt":0.4024733857216201,"score_spread":0.3310639131127687,"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."}}