{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002240795,0.001085889,0.001583209,0.005049993,0.0009971661,0.00189299,0.001261909,0.001148489,0.001102284],"category_scores_gemma":[0.005927264,0.0002860599,0.001360667,0.002647686,0.0003978384,0.001168867,0.0006576712,0.001435139,0.0007136246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001282635,"about_ca_system_score_gemma":0.001822758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02013782,"about_ca_topic_score_gemma":0.01125427,"domain_scores_codex":[0.9983442,0.0002981773,0.0001308681,0.0004951254,0.0004418589,0.0002896829],"domain_scores_gemma":[0.9961272,0.001369687,0.0002801151,0.0003199988,0.001717117,0.0001858789],"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":[0.001240452,0.001028282,0.05375066,0.0002747215,0.0003788233,0.0004123558,0.0006554368,0.1736074,0.01066129,0.004277032,0.01638776,0.7373257],"study_design_scores_gemma":[0.00001779071,0.00007199716,0.004921718,0.00002622543,0.00004611264,0.00006980926,0.000167636,0.9880333,0.002858606,0.002466049,0.001295291,0.00002551222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.241626,0.001173364,0.746713,0.0006294784,0.0003247117,0.0007220296,0.001486704,0.003982845,0.003341855],"genre_scores_gemma":[0.7471792,0.0002750348,0.2465481,0.000149822,0.0001306193,0.0003290499,0.003301817,0.0001169914,0.001969283],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02013782,"threshold_uncertainty_score":0.04004121,"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."}}