{"id":"W4386988327","doi":"10.1002/cpe.7917","title":"<scp>DeepMUI</scp>: A novel method to identify malicious users on online social network platforms","year":2023,"lang":"en","type":"article","venue":"Concurrency and Computation Practice and Experience","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Tellabs (Canada)","funders":"","keywords":"Computer science; Malware; Pooling; Metadata; Identification (biology); Dissemination; Social network (sociolinguistics); World Wide Web; Phishing; Computer security; Social media; Task (project management); Internet privacy; Data science; The Internet; Artificial intelligence; Engineering","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":[0.0005971566,0.000173328,0.0001763974,0.0001404419,0.0005935662,0.0004320032,0.0002615802,0.00008773067,0.000001291367],"category_scores_gemma":[0.0004714525,0.000169069,0.00003538802,0.00102994,0.00005040222,0.001363703,0.0001980897,0.000222823,0.00003657688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002056295,"about_ca_system_score_gemma":0.00003977917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004732537,"about_ca_topic_score_gemma":0.000004992122,"domain_scores_codex":[0.9984854,0.00007620647,0.0002665464,0.0005324502,0.0003144919,0.0003249346],"domain_scores_gemma":[0.9982796,0.001131846,0.0001753123,0.0001447168,0.0001220872,0.0001464843],"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":[0.00008679938,0.0003267783,0.0007656961,0.00007776565,0.00008705895,0.00006531415,0.1757918,0.01363367,0.003209569,0.08262619,0.01399912,0.7093303],"study_design_scores_gemma":[0.002920442,0.001893925,0.07062513,0.0002531843,0.00009734354,0.0004975437,0.03087058,0.7175232,0.00127141,0.02546765,0.1475926,0.0009869842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3699995,0.0001025864,0.6275464,0.0009115102,0.0008246807,0.0001555353,0.000004452772,0.000212476,0.0002429334],"genre_scores_gemma":[0.9632845,0.00009528245,0.03304679,0.003057201,0.0003459309,0.00005161056,0.00001784408,0.00001315584,0.00008769176],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7083433,"threshold_uncertainty_score":0.6894432,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05974817568560483,"score_gpt":0.3991297576339752,"score_spread":0.3393815819483704,"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."}}