{"id":"W4416799771","doi":"10.1109/snpd65828.2025.11253009","title":"Phishing Detection in the Gen-AI Era: Quantized LLMs vs Classical Models","year":2025,"lang":"","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Algoma University","funders":"","keywords":"Phishing; Adversarial system; Robustness (evolution); Benchmarking; Path (computing)","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002381705,0.0003907231,0.000429182,0.0005193093,0.0007516764,0.001983864,0.001723575,0.0004182891,0.00004137022],"category_scores_gemma":[0.0002080286,0.0003038271,0.0002686563,0.00296228,0.0001318955,0.002205071,0.0003834811,0.001550028,0.00006720961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002656834,"about_ca_system_score_gemma":0.000279377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001424607,"about_ca_topic_score_gemma":0.002159606,"domain_scores_codex":[0.9958771,0.0008651186,0.0007976419,0.00104709,0.0007102242,0.0007028203],"domain_scores_gemma":[0.9978803,0.0005938795,0.0001576771,0.001117797,0.0001559764,0.00009435246],"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":[0.0005758932,0.000743007,0.0003614271,0.0001326052,0.0001237733,0.00005192366,0.009826732,0.01702583,0.007524499,0.3122153,0.006202876,0.6452161],"study_design_scores_gemma":[0.001033272,0.00020693,0.001925594,0.0001131038,0.00003760255,0.00001600277,0.0001828219,0.9201324,0.004526922,0.06886986,0.002635632,0.0003198727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05425786,0.0004371056,0.9053461,0.02278558,0.004681404,0.000587809,0.00000107579,0.0002254987,0.01167756],"genre_scores_gemma":[0.990134,0.0001216688,0.001701277,0.006579299,0.0003194154,0.0000583624,9.851911e-7,0.00001506292,0.001069901],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9358762,"threshold_uncertainty_score":0.9999414,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02685801819733,"score_gpt":0.2724622875179208,"score_spread":0.2456042693205908,"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."}}