{"id":"W4414601692","doi":"10.1007/978-3-032-06078-5_8","title":"MalGPT: A Generative Explainable Model for Malware Binaries","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Defence Research and Development Canada; McGill University","funders":"","keywords":"Malware; Generative grammar; Binary number; Architecture; Natural language; Feature (linguistics); Generative model; Transformer","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005818867,0.0006595618,0.0006402814,0.001220499,0.0005722386,0.0005687811,0.003251595,0.0004184435,0.000007136816],"category_scores_gemma":[0.000206686,0.0006457779,0.0001962235,0.0006994109,0.000576956,0.001051822,0.001749556,0.0006636088,0.000006339794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005866392,"about_ca_system_score_gemma":0.001077899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008940397,"about_ca_topic_score_gemma":0.00005735804,"domain_scores_codex":[0.9960148,0.00002336558,0.0005545575,0.001962647,0.0006487569,0.0007959033],"domain_scores_gemma":[0.9968519,0.0004907397,0.0003045724,0.001569133,0.0006480885,0.0001355603],"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":[0.00002049293,0.00002662019,0.000001948521,0.0001291982,0.00001565288,0.00003891538,0.0008020597,0.2021958,0.0001876802,0.2121833,0.0004121548,0.5839862],"study_design_scores_gemma":[0.0001373568,0.0001355614,6.533427e-7,0.0001904284,0.000005081477,0.00001618424,1.626702e-7,0.6087718,0.007086887,0.3806249,0.00260072,0.000430275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000002104176,0.0004427549,0.9941996,0.0009981489,0.0009615261,0.001117925,0.00003134755,0.0006769259,0.001569715],"genre_scores_gemma":[0.004434218,0.00005136691,0.9865954,0.001872233,0.0001936373,0.0002025675,0.000007996663,0.00003868726,0.00660393],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5835559,"threshold_uncertainty_score":0.9995993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01956710397601886,"score_gpt":0.2669521346750807,"score_spread":0.2473850306990619,"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."}}