{"id":"W3133566923","doi":"10.48550/arxiv.2103.03806","title":"MalBERT: Using Transformers for Cybersecurity and Malicious Software Detection","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"","keywords":"Malware; Computer science; Software; Transformer; Computer security; Android malware; Android (operating system); Encoder; Artificial intelligence; Machine learning; Software engineering; Operating system; Engineering","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":[0.0005874436,0.0009036138,0.0003200404,0.001122802,0.0002692177,0.0008940916,0.0007665721,0.0006482516,0.002408626],"category_scores_gemma":[0.002266885,0.000311163,0.0005414315,0.0004297673,0.0006880708,0.002112255,0.0009591221,0.0008186677,0.001083984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008305455,"about_ca_system_score_gemma":0.0008198168,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005041325,"about_ca_topic_score_gemma":0.006208496,"domain_scores_codex":[0.9997272,0.0000700977,0.00001219244,0.00007901149,0.00007846992,0.00003307785],"domain_scores_gemma":[0.9994352,0.0002568614,0.00005726283,0.0001064612,0.0001080587,0.00003598573],"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":[0.0009516695,0.0002762805,0.01345182,0.0002910394,0.0001553378,0.0004304776,0.0003030238,0.2578849,0.03641049,0.05495208,0.01029248,0.6246004],"study_design_scores_gemma":[0.00001076391,0.00009128471,0.0004723207,0.00001144346,0.00002078909,0.0001274729,0.00002083501,0.9631021,0.01582982,0.01762949,0.002672067,0.00001163415],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06494668,0.0004367336,0.9117693,0.0004056684,0.00009947312,0.0001034874,0.00045286,0.01749661,0.004289238],"genre_scores_gemma":[0.8555938,0.0004664934,0.1356661,0.0001828957,0.00003865679,0.00008016063,0.0009336001,0.0005058173,0.00653242],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005041325,"threshold_uncertainty_score":0.01002395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05626123619679819,"score_gpt":0.2013812306101907,"score_spread":0.1451199944133925,"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."}}