{"id":"W4361004367","doi":"10.3390/bdcc7020060","title":"MalBERTv2: Code Aware BERT-Based Model for Malware Identification","year":2023,"lang":"en","type":"article","venue":"Big Data and Cognitive Computing","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Malware; Lexical analysis; Artificial intelligence; Source code; Machine learning; Language model; Cryptovirology; Classifier (UML); Identification (biology); Data mining; Computer security; Programming language","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004309542,0.0001512465,0.0001488983,0.0001790255,0.0003587781,0.0001851355,0.0007211909,0.00006166995,6.466318e-7],"category_scores_gemma":[0.0003560248,0.0001623631,0.00003196546,0.0004658863,0.00004962553,0.0004450505,0.0008625892,0.00009711915,0.00001654456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001630727,"about_ca_system_score_gemma":0.00006283695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006224462,"about_ca_topic_score_gemma":0.0000345159,"domain_scores_codex":[0.9985069,0.00004065721,0.0002530722,0.0007477138,0.0001695977,0.0002820383],"domain_scores_gemma":[0.9984354,0.0004993472,0.0001443075,0.0005811564,0.000270234,0.00006959886],"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":[0.00001525867,0.00002183851,0.0002010888,0.00007173984,0.00001394985,0.000005113531,0.0001585943,0.0005191292,0.0004632527,0.0007265726,0.001246067,0.9965574],"study_design_scores_gemma":[0.0003444786,0.00003242274,0.0009744338,0.0001011481,0.00001502589,0.000005107996,0.00006753134,0.9908062,0.004135999,0.002678013,0.0006353366,0.0002042742],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004147009,0.00004586269,0.9933038,0.0003530922,0.0002027999,0.0004173647,0.0005823573,0.0009106169,0.00003713517],"genre_scores_gemma":[0.9644272,0.00001127556,0.03407258,0.0003870833,0.0000935027,0.00004744095,0.0007761594,0.00002026994,0.0001644698],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9963531,"threshold_uncertainty_score":0.6620973,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1500337647012573,"score_gpt":0.3537749537692224,"score_spread":0.2037411890679651,"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."}}