{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007839832,0.0008321441,0.001873095,0.001096939,0.001097434,0.001991906,0.002046263,0.002379651,0.001711625],"category_scores_gemma":[0.03492088,0.0007115565,0.0008979876,0.0009256569,0.002121063,0.003392646,0.003589128,0.002369773,0.001772203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005953282,"about_ca_system_score_gemma":0.0007866436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001013199,"about_ca_topic_score_gemma":0.001437581,"domain_scores_codex":[0.9943157,0.002815095,0.0002277491,0.0008609044,0.001443141,0.0003375186],"domain_scores_gemma":[0.9833177,0.009211919,0.0006951973,0.004787049,0.00156931,0.0004186553],"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":[0.001469671,0.0003399396,0.01411275,0.0004510857,0.0003317649,0.000594798,0.001007499,0.06780027,0.02902781,0.07757381,0.0280043,0.7792863],"study_design_scores_gemma":[0.00004631601,0.0001516823,0.002389398,0.00006383209,0.00005838917,0.0006132572,0.0001563197,0.8903414,0.01930524,0.08220255,0.004626286,0.00004532178],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04787382,0.001251663,0.9442117,0.001596618,0.0002947887,0.0001323295,0.0002420191,0.00144946,0.002947602],"genre_scores_gemma":[0.5859465,0.0006432611,0.4019925,0.001309864,0.0007597356,0.0002377589,0.0008221003,0.0003934517,0.007894835],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007839832,"threshold_uncertainty_score":0.04146147,"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."}}