{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001646006,0.0009880437,0.001718102,0.003719851,0.0007817738,0.0009949735,0.001508525,0.001108301,0.0006011818],"category_scores_gemma":[0.002729089,0.0003115637,0.001290765,0.002259281,0.0002782508,0.001755341,0.0009012694,0.001136147,0.0005596442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007898769,"about_ca_system_score_gemma":0.001028823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01196507,"about_ca_topic_score_gemma":0.01225144,"domain_scores_codex":[0.9985794,0.0002495152,0.00008570904,0.0003774785,0.0005476628,0.0001602079],"domain_scores_gemma":[0.9984618,0.0002954341,0.0001564195,0.0002102415,0.0007946114,0.00008144668],"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":[0.000194078,0.0004762984,0.01809902,0.0001019779,0.0004061102,0.0001922305,0.0002226795,0.197668,0.00936946,0.004431846,0.008057691,0.7607807],"study_design_scores_gemma":[0.000004458469,0.00004324361,0.002146534,0.000009051508,0.00003581255,0.00009658736,0.00002856909,0.99302,0.001566895,0.001968022,0.00106416,0.00001665308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03332311,0.00074482,0.9622927,0.0001970211,0.00006892755,0.0001092194,0.0002591014,0.001785167,0.001219837],"genre_scores_gemma":[0.4706457,0.0005525283,0.5239609,0.0001765062,0.00017303,0.0001673732,0.00149338,0.0001077892,0.002722778],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01196507,"threshold_uncertainty_score":0.02379084,"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."}}