{"id":"W4391307510","doi":"10.1109/smc53992.2023.10394237","title":"How Secure is Code Generated by ChatGPT?","year":2023,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":115,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique; Cégep de l'Outaouais","funders":"","keywords":"Computer science; Code (set theory); Source code; Chatbot; Field (mathematics); Process (computing); Natural language; Code review; Artificial intelligence; Programming language; Computer security; Static program analysis; Software; Software development","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001072027,0.00007047492,0.0001048596,0.00006513445,0.00007847846,0.00003009803,0.00003903067,0.0000923215,0.0006629588],"category_scores_gemma":[0.00007382692,0.00005714967,0.0000318856,0.0004257755,0.00002322591,0.00005768591,0.00001011704,0.0001016106,0.0009537161],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003525364,"about_ca_system_score_gemma":0.0000904251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003259162,"about_ca_topic_score_gemma":0.00006389313,"domain_scores_codex":[0.9993279,0.00001341176,0.000129956,0.0001700899,0.0001438649,0.0002147509],"domain_scores_gemma":[0.9995125,0.00003167493,0.00002406028,0.0001696888,0.0001327911,0.0001292923],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001427608,0.00003193148,0.003269427,0.00003501741,0.00001278795,0.000005491531,0.001606041,0.000001369692,0.01282469,0.0002431576,0.9496067,0.03234914],"study_design_scores_gemma":[0.00004536781,0.0001667793,0.0005672302,0.00003118835,0.00002088525,0.000008062141,0.005089409,0.007081503,0.4510202,0.0006557735,0.5351762,0.0001374108],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.837181,0.0002464167,0.0004578182,0.1581147,0.0005952117,0.000257802,0.00001828808,0.0003076044,0.002821117],"genre_scores_gemma":[0.9051198,0.0003211044,0.0001300128,0.005873086,0.0004158929,0.00002366601,0.0001892085,0.00001556161,0.08791169],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4381955,"threshold_uncertainty_score":0.9998242,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1935670276868286,"score_gpt":0.4295457747303738,"score_spread":0.2359787470435452,"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."}}