{"id":"W4385409983","doi":"10.21203/rs.3.rs-3204260/v1","title":"Evaluating Supervised Machine Learning Models for Zero-Day Phishing Attack Detection: A Comprehensive Study","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Phishing; Computer science; Machine learning; Dimensionality reduction; Artificial intelligence; Data mining; Dimension (graph theory); Zero (linguistics); The Internet; World Wide Web","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":[0.01037751,0.001638149,0.001629909,0.003261043,0.0006914137,0.001524493,0.001370102,0.001438099,0.0006421263],"category_scores_gemma":[0.015015,0.0003406568,0.001777005,0.001958779,0.0006059975,0.001789711,0.0009459714,0.001558639,0.0004230324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001643937,"about_ca_system_score_gemma":0.001252545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0108919,"about_ca_topic_score_gemma":0.01062904,"domain_scores_codex":[0.9953017,0.002430057,0.000374055,0.000614777,0.001056331,0.0002229577],"domain_scores_gemma":[0.974071,0.01809317,0.001224678,0.001703886,0.004436487,0.0004706623],"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":[0.001098771,0.002603305,0.07591579,0.000996559,0.001459882,0.0001907495,0.0002585701,0.6383196,0.002066181,0.001716929,0.01023662,0.265137],"study_design_scores_gemma":[0.00002095099,0.000510192,0.00919142,0.00007396279,0.00009847378,0.00004608938,0.0001123262,0.9871621,0.00143707,0.0005883871,0.0007375546,0.00002148945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9251271,0.009234143,0.05719287,0.0009813542,0.0003263649,0.0003589752,0.001699993,0.001302637,0.003776612],"genre_scores_gemma":[0.9649133,0.00146031,0.02746044,0.0001535924,0.0001303176,0.0001437724,0.004634455,0.00006357149,0.001040247],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0108919,"threshold_uncertainty_score":0.05488217,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4647948181065284,"score_gpt":0.478203365313575,"score_spread":0.01340854720704659,"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."}}