{"id":"W4403510631","doi":"10.1109/access.2024.3482988","title":"FedITD: A Federated Parameter-Efficient Tuning With Pre-Trained Large Language Models and Transfer Learning Framework for Insider Threat Detection","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Digital and Cyber Forensics","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Insider; Insider threat; Transfer of learning; Artificial intelligence; Machine learning","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000148108,0.0001736363,0.0001593339,0.00008996361,0.0002180557,0.00191159,0.0002385881,0.00008988088,0.000001874753],"category_scores_gemma":[0.00002189006,0.0001305008,0.00005007472,0.0004074016,0.00003659802,0.001149085,0.00006094244,0.0002378611,0.000001922631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002442684,"about_ca_system_score_gemma":0.0000382485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000313877,"about_ca_topic_score_gemma":0.00007046816,"domain_scores_codex":[0.9988626,0.00002527643,0.0001485991,0.0004451042,0.0002038719,0.0003145782],"domain_scores_gemma":[0.9994646,0.0002169599,0.00002014761,0.0001563291,0.000062224,0.00007979199],"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":[0.000357135,0.0004350689,0.0002863193,0.0007166649,0.0004145094,0.000297925,0.03674492,0.1049111,0.005432117,0.1161822,0.0001624191,0.7340596],"study_design_scores_gemma":[0.0003874321,0.0002079378,0.00009177237,0.0001953833,0.00002212771,0.00003148236,0.0001375608,0.9706802,0.01096699,0.01686449,0.0001713503,0.0002432739],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4189849,0.0001403935,0.5799853,0.00007102239,0.000227967,0.0001795368,0.000005123516,0.0002472273,0.0001584765],"genre_scores_gemma":[0.9956011,0.000005688535,0.003947674,0.000160001,0.00009974286,0.00006746233,0.000005178519,0.00002469863,0.00008847931],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8657691,"threshold_uncertainty_score":0.9991245,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02306049742614485,"score_gpt":0.2854084488372936,"score_spread":0.2623479514111487,"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."}}