{"id":"W4409814264","doi":"10.1016/j.procs.2025.03.113","title":"Using Machine Learning to Analyze and Detect Anomalies in SELinux Security Policies","year":2025,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Acadia University","funders":"","keywords":"Computer science; Computer security; Artificial intelligence; Security policy; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.0009493584,0.000160733,0.0001964005,0.0008653497,0.0004692503,0.0005705142,0.0009095808,0.00004984099,0.000001631399],"category_scores_gemma":[0.00011813,0.0001568744,0.00002800167,0.004019836,0.0001870066,0.0009436541,0.001338148,0.0002596413,0.000003933745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009644789,"about_ca_system_score_gemma":0.0001909029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002780672,"about_ca_topic_score_gemma":0.0002721545,"domain_scores_codex":[0.9982432,0.00006316678,0.0002608252,0.0006789326,0.000308907,0.0004450282],"domain_scores_gemma":[0.9992868,0.00008876179,0.00006461615,0.0002819094,0.0001440386,0.0001338818],"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":[0.00006900489,0.0002176316,0.1133096,0.0003335025,0.00003112153,0.00005508464,0.03514867,0.06324004,0.01869834,0.04758237,0.0002190186,0.7210956],"study_design_scores_gemma":[0.0001448599,0.00008486208,0.005654848,0.00007988192,0.000002332552,0.0000288494,0.00001786097,0.9836026,0.005015638,0.00413257,0.001058201,0.0001774862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4786338,0.0002837716,0.5198665,0.0004635191,0.0003670359,0.0001369042,3.390589e-7,0.0001156832,0.0001324818],"genre_scores_gemma":[0.8857551,0.00004385919,0.1133543,0.0007439968,0.00007992672,0.000006500558,1.492781e-7,0.000003512074,0.00001262131],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9203626,"threshold_uncertainty_score":0.6397152,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01248245314128107,"score_gpt":0.26694520520652,"score_spread":0.254462752065239,"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."}}