{"id":"W7127344164","doi":"10.1109/ccece64018.2025.11364452","title":"How Effective are pretrained Programming Language-based Language Models (PLLMs) in the Detection of Android Vulnerabilities?","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"Science and Engineering Research Council","keywords":"Android (operating system); Language model; Vulnerability (computing); Mobile device; Multiple Models; Android application","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":[0.001985045,0.002088367,0.0008644974,0.001138612,0.0003457252,0.001306282,0.001495356,0.001185515,0.001434471],"category_scores_gemma":[0.008271853,0.000516198,0.001232681,0.0004899933,0.0004796014,0.003029732,0.0008281932,0.00259318,0.001704258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008766953,"about_ca_system_score_gemma":0.001539247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009932244,"about_ca_topic_score_gemma":0.01622659,"domain_scores_codex":[0.9990091,0.0003338759,0.0000625115,0.0003404339,0.0001292647,0.0001247841],"domain_scores_gemma":[0.9973742,0.001566634,0.0001800477,0.0003274932,0.0004219969,0.0001296825],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001559903,0.001519769,0.04470034,0.0007835987,0.0007038983,0.0005295873,0.0003738782,0.2202454,0.02010575,0.002393558,0.02622833,0.680856],"study_design_scores_gemma":[0.0000600673,0.0003812585,0.003099903,0.0001021954,0.0001360479,0.000186027,0.0001554877,0.9813855,0.009421779,0.002170718,0.002859319,0.00004170028],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.780555,0.009111207,0.1686914,0.004749703,0.001071621,0.0004405207,0.004925645,0.02106804,0.009386801],"genre_scores_gemma":[0.9302951,0.001257772,0.05769705,0.001016617,0.0001167118,0.0001608304,0.005855111,0.0003417392,0.00325927],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009932244,"threshold_uncertainty_score":0.01974887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008168571883936345,"score_gpt":0.2613502313963667,"score_spread":0.2531816595124304,"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."}}