{"id":"W4399687987","doi":"10.1145/3673660.3655042","title":"A Large Scale Study and Classification of VirusTotal Reports on Phishing and Malware URLs","year":2024,"lang":"en","type":"article","venue":"ACM SIGMETRICS Performance Evaluation Review","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Phishing; Malware; Computer science; Computer security; Classifier (UML); World Wide Web; The Internet; Artificial intelligence","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":[0.005056787,0.0004334681,0.000493497,0.0147466,0.0008095267,0.001356273,0.0004941049,0.0006537691,0.0006224999],"category_scores_gemma":[0.02751137,0.0002521954,0.0005277512,0.008607036,0.0006740893,0.00237287,0.001108287,0.0008578337,0.0009004145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007205943,"about_ca_system_score_gemma":0.0007115273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006159107,"about_ca_topic_score_gemma":0.01041498,"domain_scores_codex":[0.9941201,0.001655134,0.0006979618,0.001043092,0.002152842,0.0003307936],"domain_scores_gemma":[0.9351599,0.02462474,0.01962958,0.004090851,0.01471138,0.001783438],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001374313,0.0002487999,0.9185413,0.0006242798,0.0002974414,0.0002806389,0.002976034,0.000469155,0.002106203,0.0003746209,0.006677379,0.06726672],"study_design_scores_gemma":[0.000007492637,0.0002282229,0.9867357,0.0001825616,0.0001000651,0.0005820296,0.001957914,0.003160284,0.001240949,0.0001500621,0.005612235,0.00004243795],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9881269,0.002661708,0.001708617,0.0002712625,0.00006030765,0.0001694706,0.005035812,0.0001816436,0.001784302],"genre_scores_gemma":[0.9841366,0.00161644,0.00314578,0.0001541682,0.0001411209,0.0001353425,0.009403457,0.000058612,0.001208473],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0147466,"threshold_uncertainty_score":0.02674317,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07357319126989516,"score_gpt":0.351201693127919,"score_spread":0.2776285018580238,"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."}}