{"id":"W4297495481","doi":"10.1007/978-981-19-4193-1_64","title":"NO PHISHING! Noise Resistant Data Resampling in Majority-Biased Detection of Malicious Websites","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Undersampling; Oversampling; Resampling; Phishing; Computer science; Noise (video); Class (philosophy); Data mining; Machine learning; Artificial intelligence; Pattern recognition (psychology); World Wide Web; Computer network; The Internet; Bandwidth (computing)","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001507434,0.0003608707,0.0006692075,0.000421722,0.0001647515,0.0002650541,0.001029221,0.000527728,0.00001714719],"category_scores_gemma":[0.0001953534,0.0003612053,0.00007183703,0.0002995819,0.00004942268,0.0003087846,0.000604816,0.001191466,0.000002240787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001868123,"about_ca_system_score_gemma":0.00005482125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002931568,"about_ca_topic_score_gemma":0.003885112,"domain_scores_codex":[0.9973227,0.0001865166,0.0007739335,0.0009446203,0.0004382253,0.0003340048],"domain_scores_gemma":[0.9972427,0.0007923673,0.0004931683,0.00132953,0.00007650558,0.00006565249],"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":[0.001165023,0.0001911663,0.003903015,0.002999627,0.0003712909,0.0007041184,0.002074608,0.8514892,0.006173497,0.03032618,0.000700007,0.09990219],"study_design_scores_gemma":[0.0007153222,0.0003367972,0.0003586276,0.00162425,0.00004366012,0.00006007448,0.00000505044,0.9370852,0.00004701006,0.005840866,0.05311311,0.0007700432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002261794,0.04699368,0.9263704,0.000203963,0.00938269,0.001725162,0.0001537293,0.0002927597,0.01261576],"genre_scores_gemma":[0.9963188,0.0008318342,0.0007149448,0.00008521193,0.0008745027,0.00002851703,0.0001248507,0.00006120096,0.0009601249],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.994057,"threshold_uncertainty_score":0.999884,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03054820319736598,"score_gpt":0.2362676637370595,"score_spread":0.2057194605396935,"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."}}