{"id":"W4311785321","doi":"10.5267/j.ijdns.2022.10.002","title":"Employing cluster-based class decomposition approach to detect phishing websites using machine learning classifiers","year":2022,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Applied Science Private University","keywords":"Phishing; Random forest; Computer science; Feature selection; Machine learning; Artificial intelligence; Heuristics; Data mining; Feature (linguistics); Class (philosophy); Decision tree; The Internet; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003155925,0.0001030259,0.0001339164,0.0004145594,0.001011556,0.0007936442,0.003057844,0.00002041311,0.000005639826],"category_scores_gemma":[0.0001507365,0.00009992696,0.00003873942,0.000861905,0.00007837039,0.002369268,0.001577999,0.0004268436,8.509385e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002197655,"about_ca_system_score_gemma":0.0001726753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000380251,"about_ca_topic_score_gemma":0.000007873929,"domain_scores_codex":[0.9977791,0.0001627388,0.0003286251,0.0003784296,0.001109248,0.0002418865],"domain_scores_gemma":[0.9988523,0.0001852288,0.0003502383,0.0002687142,0.000200645,0.0001428375],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001575607,0.00006526904,0.008540251,0.000005766665,0.00004451051,0.00002949732,0.0005299636,0.9297702,0.01253009,0.0005675423,0.0006057601,0.04715356],"study_design_scores_gemma":[0.0003180164,0.0001589825,0.0007484215,0.00003828277,0.000009677771,0.0005312829,0.00005101342,0.9921799,0.0004093836,0.0003325689,0.005099602,0.0001228521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1621445,0.0001938737,0.8352377,0.0006622044,0.001524235,0.00006221468,0.00000926179,0.00002732857,0.0001386839],"genre_scores_gemma":[0.8360304,0.00001074464,0.1630708,0.0005479169,0.0003198055,0.000001412155,0.000008843705,0.000005927668,0.000004174047],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6738859,"threshold_uncertainty_score":0.7780174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05230284582837775,"score_gpt":0.3189974287512063,"score_spread":0.2666945829228285,"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."}}