{"id":"W4399567378","doi":"10.1145/3650105.3652299","title":"Fine Tuning Large Language Model for Secure Code Generation","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; Concordia University","funders":"","keywords":"Computer science; Code (set theory); Code generation; Vulnerability (computing); Face (sociological concept); Source code; Programming language; Computer security","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001942916,0.001641348,0.0008029478,0.001070702,0.0005170935,0.001439859,0.002558353,0.001407528,0.003645814],"category_scores_gemma":[0.01066158,0.0007886994,0.001639328,0.0007348386,0.0007054153,0.0031833,0.001584016,0.003510322,0.003353844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001465243,"about_ca_system_score_gemma":0.002805065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008809023,"about_ca_topic_score_gemma":0.016158,"domain_scores_codex":[0.9985341,0.0004178384,0.00009625067,0.0005093142,0.0002670804,0.0001753053],"domain_scores_gemma":[0.9962115,0.001802008,0.0002036895,0.0008979088,0.0007125066,0.0001723267],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00080011,0.0009831347,0.01510912,0.0008434674,0.0003517591,0.0007073968,0.0005395258,0.4676377,0.04772319,0.005292892,0.0676126,0.3923991],"study_design_scores_gemma":[0.0001039121,0.0001172233,0.0007078695,0.00003528491,0.00006138721,0.0001401939,0.00007180561,0.9719416,0.01428317,0.00389389,0.008606552,0.00003714874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3428994,0.003659583,0.4769971,0.00231668,0.001191506,0.0007530602,0.005582422,0.1559913,0.01060904],"genre_scores_gemma":[0.6390398,0.0006772025,0.3270249,0.002046398,0.0001259437,0.0007399163,0.01645758,0.007024407,0.006863843],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008809023,"threshold_uncertainty_score":0.01751554,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03353709414965798,"score_gpt":0.312070987112272,"score_spread":0.278533892962614,"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."}}