{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001493608,0.0002562068,0.000253857,0.0002373405,0.0002136474,0.0004916823,0.0003837424,0.0001584792,0.0002714969],"category_scores_gemma":[0.00006084871,0.0002810629,0.00009819131,0.0003121673,0.00007420692,0.0005631642,0.00009292907,0.0002801832,0.00004729832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001862871,"about_ca_system_score_gemma":0.0001542799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009443992,"about_ca_topic_score_gemma":0.0005283257,"domain_scores_codex":[0.9977108,0.0001476311,0.0004861572,0.0007702093,0.0006377387,0.0002474309],"domain_scores_gemma":[0.9984277,0.0001559696,0.0002055093,0.0003744697,0.0007112173,0.0001250565],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000286774,0.0008190097,0.003661175,0.0002034671,0.001250989,0.0006015399,0.003510325,0.01203434,0.4800321,0.3253559,0.001870326,0.1703741],"study_design_scores_gemma":[0.001510283,0.0002673682,0.004211971,0.0006380486,0.00009547301,0.000725252,0.002152195,0.6471274,0.2794214,0.016993,0.04539733,0.001460246],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05331163,0.0001948697,0.9236042,0.0006616214,0.003534569,0.0002217231,0.0001128901,0.000192986,0.01816547],"genre_scores_gemma":[0.9845886,0.0004340612,0.008816333,0.000179043,0.0003663859,0.00007472032,0.00004697547,0.0000251589,0.005468735],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.931277,"threshold_uncertainty_score":0.9999642,"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."}}