{"id":"W4324118134","doi":"10.1109/bdcat56447.2022.00018","title":"Mining Large Data to Create a Balanced Vulnerability Detection Dataset for Embedded Linux System","year":2022,"lang":"en","type":"article","venue":"","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hacker; Computer science; Firmware; Vulnerability (computing); Computer security; Linux kernel; Embedded system; Operating system","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001613594,0.001850878,0.0009076578,0.003843771,0.001145854,0.001251644,0.002467822,0.002339609,0.001559643],"category_scores_gemma":[0.005478121,0.0004667582,0.001682258,0.002909135,0.0007201182,0.001858073,0.001716347,0.002805883,0.002233186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001392466,"about_ca_system_score_gemma":0.001773761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01291583,"about_ca_topic_score_gemma":0.0271007,"domain_scores_codex":[0.9976362,0.0002949638,0.0002620449,0.0007691087,0.0007121469,0.0003255965],"domain_scores_gemma":[0.9971381,0.0007551461,0.0002422058,0.0007206399,0.0008901296,0.0002537172],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00123852,0.00317892,0.1285297,0.002981616,0.0009060797,0.002323797,0.0005048205,0.05497104,0.01961153,0.003674666,0.5460032,0.2360761],"study_design_scores_gemma":[0.0006556147,0.001528247,0.1991695,0.0007334852,0.000540473,0.003463088,0.001375989,0.3907512,0.0403636,0.01067972,0.3502835,0.0004555946],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.3504233,0.003729368,0.0261069,0.002879717,0.001007621,0.0007725156,0.598216,0.01085308,0.006011492],"genre_scores_gemma":[0.1397591,0.0005660925,0.03459377,0.0005124061,0.0001037147,0.0004255433,0.8216714,0.0002215637,0.002146302],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01291583,"threshold_uncertainty_score":0.02568126,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05378122401371729,"score_gpt":0.3368215604977142,"score_spread":0.283040336483997,"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."}}