{"id":"W2913576447","doi":"10.1109/tifs.2019.2895963","title":"Large-Scale Empirical Study of Important Features Indicative of Discovered Vulnerabilities to Assess Application Security","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Information Forensics and Security","topic":"Software Engineering Research","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Feature selection; Vulnerability (computing); Secure coding; Scale (ratio); Empirical research; Machine learning; Feature (linguistics); Data science; Predictive power; Focus (optics); Selection (genetic algorithm); Data mining; Artificial intelligence; Computer security; Information security; Software security assurance; Statistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004180901,0.0001213694,0.0002266712,0.0002458029,0.00008016,0.00005365082,0.0002630183,0.00007484063,0.000007055939],"category_scores_gemma":[0.00004257721,0.0001097957,0.00005086419,0.0004918724,0.00004085172,0.0007768154,0.00001440864,0.0002490709,0.000004644357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004375165,"about_ca_system_score_gemma":0.000058351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008578285,"about_ca_topic_score_gemma":0.00008806834,"domain_scores_codex":[0.9986898,0.00004785912,0.0004382803,0.0001809121,0.0004790497,0.0001640531],"domain_scores_gemma":[0.9986984,0.0002764652,0.000239142,0.0004556316,0.0002417974,0.00008857036],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0005067826,0.003519553,0.2063926,0.001259673,0.0003824482,0.000001367078,0.7103786,0.03707402,0.000548939,0.02468816,0.000685382,0.01456249],"study_design_scores_gemma":[0.006561864,0.006190544,0.5337434,0.0002002788,0.00009218409,0.00002588044,0.04612594,0.3013636,0.07812694,0.02496556,0.001157442,0.001446432],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6020181,0.000003735765,0.3971986,0.00004903538,0.00009368792,0.0004809322,0.00008841038,0.00002989676,0.00003764429],"genre_scores_gemma":[0.9987844,0.000006424464,0.001088901,0.0000374632,0.000005134025,0.0000591322,0.00000915402,0.000004461276,0.000004938812],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6642527,"threshold_uncertainty_score":0.447734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01225166794696762,"score_gpt":0.2836587495156881,"score_spread":0.2714070815687205,"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."}}