{"id":"W2158063174","doi":"10.1109/tnn.2011.2161999","title":"Textual and Visual Content-Based Anti-Phishing: A Bayesian Approach","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":197,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Phishing; Computer science; Naive Bayes classifier; Artificial intelligence; Classifier (UML); Web page; Machine learning; Bayes classifier; Pattern recognition (psychology); Data mining; The Internet; Support vector machine; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001656433,0.0002194931,0.0001960696,0.0001552509,0.0003374431,0.000186841,0.0003267243,0.0001524381,0.00001753727],"category_scores_gemma":[0.000002469206,0.0002043301,0.0001088756,0.0004183562,0.00008946904,0.0005368607,0.000003370998,0.0004684671,0.000004912212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002500747,"about_ca_system_score_gemma":0.00001740835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001128796,"about_ca_topic_score_gemma":0.00003163092,"domain_scores_codex":[0.9986111,0.0001138342,0.000225198,0.0004994015,0.0002026885,0.0003478047],"domain_scores_gemma":[0.999332,0.00008747922,0.00007204079,0.0002888415,0.00004288594,0.0001767389],"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":[0.0006291369,0.002091733,0.001402924,0.00007785891,0.0002282063,0.0001230332,0.001908801,0.2231759,0.003310836,0.002238291,0.0005531529,0.7642601],"study_design_scores_gemma":[0.0005271015,0.0003680465,0.001346371,0.00001424264,0.00002129596,0.00004785171,0.00004507943,0.9941092,0.003224635,0.00002376337,0.00002888913,0.0002435847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03390646,0.00004391173,0.9640924,0.0001272089,0.0007697891,0.0001966452,0.000002011478,0.0003505918,0.0005110329],"genre_scores_gemma":[0.9930568,0.000008670511,0.00609583,0.000635927,0.00009297181,0.00002911211,0.00000121733,0.00001975161,0.00005974351],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9591503,"threshold_uncertainty_score":0.8332338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04666925283207304,"score_gpt":0.2297973862758755,"score_spread":0.1831281334438024,"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."}}