{"id":"W4389628379","doi":"10.1145/3626790","title":"A Large Scale Study and Classification of VirusTotal Reports on Phishing and Malware URLs","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Phishing; Malware; Computer science; Computer security; Classifier (UML); World Wide Web; Artificial intelligence; The Internet","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":[0.003241325,0.0004090817,0.0004251552,0.01103485,0.0008195158,0.001302404,0.0005015884,0.0008082345,0.000619451],"category_scores_gemma":[0.01997625,0.000257452,0.0004742418,0.006098134,0.000849365,0.002500161,0.001354581,0.0009403013,0.0008532124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000554295,"about_ca_system_score_gemma":0.0004603546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004050327,"about_ca_topic_score_gemma":0.005953555,"domain_scores_codex":[0.9959293,0.001067525,0.0004464862,0.0009128785,0.001355913,0.0002877631],"domain_scores_gemma":[0.9579546,0.01727939,0.01275598,0.003606556,0.006796991,0.001606574],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001041071,0.0002146218,0.9592955,0.0002111943,0.000145692,0.0004008707,0.004391697,0.0004054158,0.002856505,0.0002737985,0.002564379,0.02913639],"study_design_scores_gemma":[0.000004972932,0.0001615595,0.9885479,0.00007092267,0.00004380308,0.0007205777,0.00247403,0.003745037,0.001338565,0.0001470369,0.002709028,0.00003651134],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9959003,0.0003165257,0.0008475244,0.00007573208,0.00001881268,0.0000702613,0.002004828,0.00009655752,0.0006695024],"genre_scores_gemma":[0.9916546,0.0002723207,0.002123607,0.00006696203,0.00005754141,0.00007536753,0.005051774,0.0000419407,0.0006558588],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01103485,"threshold_uncertainty_score":0.017142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04809515265651458,"score_gpt":0.2658897913176593,"score_spread":0.2177946386611447,"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."}}