{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006597077,0.001180351,0.0005371845,0.001046416,0.0005960413,0.001724072,0.002453232,0.002116877,0.01268932],"category_scores_gemma":[0.004505763,0.0009322917,0.00230553,0.0006042626,0.00119679,0.00309055,0.002016539,0.003034036,0.002360101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001077873,"about_ca_system_score_gemma":0.0009409614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004440565,"about_ca_topic_score_gemma":0.005408008,"domain_scores_codex":[0.9995813,0.0001261612,0.00001917836,0.0001018495,0.0001277869,0.00004379204],"domain_scores_gemma":[0.9986111,0.0009488518,0.00005807667,0.000238612,0.00010195,0.00004145367],"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":[0.00009033587,0.00007609103,0.001159079,0.0002182015,0.00008165292,0.0004127609,0.0005209806,0.5610784,0.003726625,0.370375,0.01004945,0.05221137],"study_design_scores_gemma":[0.00001345335,0.00001154531,0.00008325112,0.00001721154,0.00001889022,0.0000701652,0.00001349734,0.8407871,0.001094364,0.1494894,0.008389335,0.00001182155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00644182,0.0001394074,0.981833,0.0004873572,0.00006420425,0.00008015167,0.001121692,0.00431963,0.005512696],"genre_scores_gemma":[0.3971894,0.0008020953,0.5664778,0.0006375197,0.0001537198,0.0008318671,0.004119362,0.004369084,0.02541901],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01268932,"threshold_uncertainty_score":0.04245001,"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."}}