{"id":"W4220949653","doi":"10.3390/app12062806","title":"Investigating the Influence of Feature Sources for Malicious Website Detection","year":2022,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Credential; Machine learning; Pipeline (software); Feature (linguistics); Artificial intelligence; JavaScript; Classifier (UML); Information retrieval; World Wide Web; Data mining; Computer security","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":[0.002465504,0.002042329,0.0006789442,0.002548822,0.0005413007,0.001815285,0.0009490561,0.001462827,0.001036298],"category_scores_gemma":[0.01078405,0.000270165,0.0009933842,0.001219106,0.0006952832,0.002814245,0.001007571,0.002434263,0.001189794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000763416,"about_ca_system_score_gemma":0.0006489791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008991957,"about_ca_topic_score_gemma":0.01278023,"domain_scores_codex":[0.9982526,0.0005742332,0.0001212352,0.0005565991,0.0002986949,0.0001966162],"domain_scores_gemma":[0.9916024,0.005632419,0.0005589858,0.001044433,0.0008515635,0.0003102549],"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":[0.002358311,0.002807161,0.3469853,0.001102979,0.001062268,0.0009567732,0.000563711,0.1314537,0.01769084,0.002807614,0.05745748,0.4347539],"study_design_scores_gemma":[0.0001138106,0.001014376,0.09161911,0.0001632066,0.000347692,0.0009827885,0.0008772949,0.8641215,0.02470344,0.004037768,0.01189318,0.0001258563],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9641227,0.00348039,0.01583042,0.001185992,0.0004561299,0.0001029887,0.008276777,0.002389793,0.004154826],"genre_scores_gemma":[0.9647941,0.0004272867,0.0125623,0.0001877061,0.0001343498,0.00005017161,0.0201225,0.0001111625,0.001610413],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008991957,"threshold_uncertainty_score":0.01787925,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01434478936728336,"score_gpt":0.2277430551105599,"score_spread":0.2133982657432765,"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."}}