{"id":"W7127987698","doi":"10.1109/commantel68363.2025.11368437","title":"Hybrid Machine Learning and GenAI Approach for Data Loss Prevention","year":2025,"lang":"","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Paraphrase; Classifier (UML); Baseline (sea); Machine translation; Pipeline (software); Ensemble learning; Decision tree; Confusion matrix","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":[0.001226065,0.0001893945,0.0002068932,0.0001479131,0.0005430293,0.0006571018,0.000872875,0.00007893816,0.00002522329],"category_scores_gemma":[0.0001774334,0.0001866299,0.00005772755,0.0003039269,0.00005993839,0.000919879,0.001185395,0.0002648993,0.000004233677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003104355,"about_ca_system_score_gemma":0.00009717306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001500351,"about_ca_topic_score_gemma":0.00001509039,"domain_scores_codex":[0.9981104,0.0001422993,0.0003061584,0.0009822705,0.0001665855,0.000292295],"domain_scores_gemma":[0.99884,0.0001263343,0.0001163259,0.0007707025,0.00007502879,0.0000716091],"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":[0.00008786737,0.0002172881,0.002996878,0.0006902643,0.0001410132,0.000002027805,0.0002071584,0.0001961119,0.0002455525,0.01317387,0.003848033,0.9781939],"study_design_scores_gemma":[0.0006709949,0.0001835758,0.000263588,0.00005334304,0.00006646065,0.00002242098,0.00001472303,0.9599315,0.0009463948,0.004023271,0.03363635,0.0001873912],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002996867,0.00258481,0.9886316,0.0005987298,0.0008173221,0.0005633316,0.00001824771,0.0001231595,0.003665918],"genre_scores_gemma":[0.8205956,0.0004840629,0.1564386,0.0001852259,0.0001985233,0.00002996203,0.0002250153,0.00001412576,0.0218289],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9780065,"threshold_uncertainty_score":0.7610546,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03970518838716456,"score_gpt":0.2961216465767995,"score_spread":0.2564164581896349,"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."}}