{"id":"W4406892885","doi":"10.1109/csnet64211.2024.10851753","title":"Chat or Trap? Detecting Scams in Messaging Applications with Large Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Trap (plumbing); Computer science; Instant messaging; World Wide Web; Internet privacy; Computer security; Physics","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":[0.0002776334,0.00007940443,0.00007186776,0.0001549956,0.00008503644,0.0002765076,0.0002487645,0.00003303587,0.00001742079],"category_scores_gemma":[0.000003967752,0.00005538499,0.00002096313,0.0008492324,0.000007613796,0.0006747978,0.00005462015,0.0001424086,0.00002238839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003654675,"about_ca_system_score_gemma":0.00003705652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001466267,"about_ca_topic_score_gemma":0.0008175894,"domain_scores_codex":[0.9992545,0.0000200558,0.0001013575,0.0002984653,0.0001314061,0.0001941844],"domain_scores_gemma":[0.9996191,0.00006938155,0.00001486651,0.0002477125,0.00001208712,0.00003684471],"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":[0.00003083484,0.0001444033,0.0005346616,0.0002452687,0.00005595327,0.0002004794,0.02850259,0.006603261,0.006009589,0.3057085,0.0002050221,0.6517594],"study_design_scores_gemma":[0.0001877995,0.00003945038,0.0001175508,0.00008758596,0.000004485974,0.00005406448,0.0005982168,0.9892119,0.005180477,0.00289062,0.001461902,0.0001659767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02306559,0.0003056328,0.9681573,0.0002988755,0.00007109451,0.0001579533,7.490528e-7,0.0005506269,0.00739216],"genre_scores_gemma":[0.9866207,0.000006718796,0.01245832,0.0001163568,0.00004782349,0.00007575892,7.499099e-7,0.00000991413,0.0006636708],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9826086,"threshold_uncertainty_score":0.2666369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01514962120186019,"score_gpt":0.2584220733025996,"score_spread":0.2432724521007394,"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."}}