{"id":"W4401453369","doi":"10.1109/hsi61632.2024.10613528","title":"Evaluating the Efficacy of Large Language Models in Identifying Phishing Attempts","year":2024,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Phishing; Natural language processing; Artificial intelligence; World Wide Web; 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":[0.01920869,0.002396206,0.001519763,0.002269155,0.001031461,0.00265185,0.001607196,0.00248914,0.001652309],"category_scores_gemma":[0.0661779,0.0007802634,0.001641042,0.00102347,0.001073976,0.004081327,0.001542141,0.003115004,0.001260882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002040934,"about_ca_system_score_gemma":0.00214274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01345715,"about_ca_topic_score_gemma":0.01270191,"domain_scores_codex":[0.9892374,0.007433068,0.0009153701,0.001352343,0.0006886676,0.0003731879],"domain_scores_gemma":[0.8393065,0.1483593,0.002953721,0.00397475,0.003938544,0.001466986],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.02014716,0.01239447,0.183191,0.002077085,0.002780337,0.0006216367,0.002351023,0.3856089,0.01321063,0.00265751,0.01141439,0.3635458],"study_design_scores_gemma":[0.0002906351,0.002295605,0.01131278,0.00009338287,0.0004535885,0.00015649,0.000555517,0.9781693,0.004396295,0.001485097,0.0006983093,0.00009298555],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9636861,0.001534023,0.02644645,0.001177058,0.0002592955,0.0005539521,0.001599126,0.001800634,0.002943293],"genre_scores_gemma":[0.9722926,0.0002692182,0.02381985,0.0002450526,0.00008281096,0.0002555317,0.002145051,0.00008380038,0.0008061241],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01920869,"threshold_uncertainty_score":0.1015865,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08775558757171041,"score_gpt":0.3856797926472156,"score_spread":0.2979242050755052,"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."}}