{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003486636,0.0001192796,0.0003921752,0.0004255546,0.0001725071,0.0001222221,0.0003992691,0.00004171651,1.432515e-7],"category_scores_gemma":[0.0004755606,0.00008932185,0.00008010998,0.00120944,0.00003534488,0.0001495908,0.0003625664,0.00009030677,1.32982e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002516302,"about_ca_system_score_gemma":0.000009471913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004748243,"about_ca_topic_score_gemma":0.000007523402,"domain_scores_codex":[0.9981687,0.00003919955,0.0005017937,0.0003637666,0.0007956923,0.0001308341],"domain_scores_gemma":[0.9983891,0.00007918257,0.0007857932,0.0003473847,0.0003595965,0.00003890344],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003977884,0.0002863178,0.9057496,0.000512647,0.000929612,8.520426e-7,0.01284895,0.0007338057,0.07446596,0.001052148,0.0002703998,0.003109891],"study_design_scores_gemma":[0.0003646137,0.000325846,0.8123959,0.0005625869,0.0004801446,0.000004621219,0.002900153,0.178434,0.004131499,0.0002364276,0.00001759543,0.0001465621],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9988073,0.000105684,0.0003597913,0.0001875755,0.0001348978,0.0002574915,0.000001401166,0.0000445836,0.0001012741],"genre_scores_gemma":[0.9998101,0.000007343403,0.0001259724,0.000007658501,0.00002783557,0.000004006857,4.356405e-7,0.000005484516,0.00001116842],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1777002,"threshold_uncertainty_score":0.3642439,"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."}}