{"id":"W4404740962","doi":"10.1109/mobisecserv63327.2024.10760006","title":"Leveraging Human Knowledge in Large Language Model for Obfuscation-Resisted Phishing URL Detection","year":2024,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; McGill University","funders":"","keywords":"Obfuscation; Phishing; Computer science; Malware; Computer security; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000567469,0.000105716,0.000094555,0.0002997565,0.0001961521,0.0004069453,0.0002821217,0.00007009106,0.000008624814],"category_scores_gemma":[0.00003464308,0.0001055728,0.00006855998,0.0005189645,0.000006451789,0.0007726991,0.00007300521,0.0001491277,0.00002442688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001474886,"about_ca_system_score_gemma":0.00004349502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000140983,"about_ca_topic_score_gemma":0.00159848,"domain_scores_codex":[0.9990599,0.00003471888,0.0001915988,0.0003749277,0.0001055486,0.0002333232],"domain_scores_gemma":[0.9995472,0.00009972755,0.00002532215,0.0002471607,0.00004128688,0.00003927596],"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":[0.00002806598,0.0003848968,0.0004626299,0.000760281,0.00008311774,0.00002299041,0.08780728,0.008880432,0.335,0.2250378,0.003201747,0.3383307],"study_design_scores_gemma":[0.0002226691,0.00001983975,0.000611881,0.0000536547,0.000004831504,0.000003203732,0.0001254662,0.984563,0.009768903,0.003684888,0.0008022311,0.0001394509],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.110892,0.0004131063,0.8843973,0.0001886537,0.0005537619,0.0001825007,0.000001549874,0.0005604493,0.002810634],"genre_scores_gemma":[0.9930303,0.000002214856,0.004600264,0.00007111153,0.0001434292,0.00006389566,0.000006115232,0.00001492979,0.002067748],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9756826,"threshold_uncertainty_score":0.4305133,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03461630860754857,"score_gpt":0.3107950751636736,"score_spread":0.2761787665561251,"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."}}