{"id":"W4205635956","doi":"10.1109/smc52423.2021.9659287","title":"MalBERT: Malware Detection using Bidirectional Encoder Representations from Transformers","year":2021,"lang":"en","type":"article","venue":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Malware; Computer science; Encoder; Transformer; Software; Artificial intelligence; Android (operating system); Android malware; Machine learning; Computer security; Operating system; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003082079,0.0008283511,0.0004404033,0.0007753689,0.0002247376,0.0006898196,0.0008382217,0.0005847773,0.001859782],"category_scores_gemma":[0.001498229,0.0002973007,0.0005691539,0.0003303945,0.0004175119,0.001183389,0.0007455148,0.0008302195,0.0006505539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007013846,"about_ca_system_score_gemma":0.0008852982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006898152,"about_ca_topic_score_gemma":0.008136853,"domain_scores_codex":[0.9998381,0.00003391812,0.000007647356,0.00004412836,0.00004599138,0.00003022633],"domain_scores_gemma":[0.9996411,0.0001635988,0.00003908021,0.00005190482,0.00008053087,0.00002372522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006009037,0.0002733511,0.005432507,0.0001627271,0.0001398931,0.0003729317,0.000154478,0.5198681,0.02601828,0.02146078,0.006764765,0.4187513],"study_design_scores_gemma":[0.000007344452,0.00003839036,0.0001941722,0.000005765474,0.00001000381,0.00004593054,0.000007503771,0.9904391,0.004201803,0.004492981,0.0005513511,0.000005703785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08505253,0.0004279664,0.9003739,0.0003262684,0.00009163431,0.00011093,0.0006072387,0.009000166,0.004009335],"genre_scores_gemma":[0.8855376,0.0002880612,0.106127,0.0001793893,0.00003225002,0.0001372298,0.001229347,0.0002915561,0.006177492],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006898152,"threshold_uncertainty_score":0.01371604,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05917844192296761,"score_gpt":0.3156435808767698,"score_spread":0.2564651389538022,"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."}}