{"id":"W4360777922","doi":"10.5267/j.ijdns.2023.1.003","title":"A new phishing-website detection framework using ensemble classification and clustering","year":2023,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Random forest; Phishing; Ensemble learning; Computer science; Cluster analysis; Classifier (UML); Artificial intelligence; Machine learning; Data mining; Feature (linguistics); Ensemble forecasting; Pattern recognition (psychology); 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":[0.0015098,0.00007046882,0.00008919207,0.0002680845,0.0002426901,0.0008226458,0.001374338,0.00004024298,0.000001619448],"category_scores_gemma":[0.0002218731,0.00006497889,0.00001626242,0.0008452679,0.00007377955,0.003557168,0.0007536254,0.0001774542,0.000002631788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005133604,"about_ca_system_score_gemma":0.0001198056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003465253,"about_ca_topic_score_gemma":0.00002311616,"domain_scores_codex":[0.9987435,0.00002896725,0.0002394442,0.0002740134,0.0005472759,0.0001667471],"domain_scores_gemma":[0.9990476,0.0001432011,0.0002501939,0.0002583712,0.0001792331,0.0001214307],"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":[0.00005502269,0.0000124168,0.00602432,0.000006730836,0.00003759538,0.00003151424,0.0009792391,0.00456103,0.03145736,0.003044502,0.0009399163,0.9528503],"study_design_scores_gemma":[0.0001742118,0.00004965682,0.02201077,0.0001356957,0.000008563309,0.0004417511,0.00004383826,0.9638034,0.0004784869,0.01069815,0.002058507,0.00009694357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1487785,0.0001549491,0.848107,0.0006913199,0.002173832,0.00002810118,0.000001492423,0.00003030371,0.00003450137],"genre_scores_gemma":[0.9143943,0.0002983633,0.08427221,0.0001089516,0.0009096374,2.163807e-7,0.00000122849,0.000003757872,0.00001134079],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9592424,"threshold_uncertainty_score":0.7932792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08063551838146381,"score_gpt":0.3427147751419228,"score_spread":0.262079256760459,"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."}}