{"id":"W4406460194","doi":"10.1109/tps-isa62245.2024.00043","title":"Fine-Tuning LLMs for Code Mutation: A New Era of Cyber Threats","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Computer security; Code (set theory); Mutation; Internet privacy; Programming language; Genetics; Biology","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":[0.001697894,0.001151465,0.0006949453,0.0006231804,0.0003873893,0.001011309,0.001690237,0.001236989,0.001248813],"category_scores_gemma":[0.01055343,0.0005223413,0.000787362,0.0002794064,0.001183491,0.002182141,0.001409281,0.002534445,0.000892844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008934576,"about_ca_system_score_gemma":0.001630753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00324369,"about_ca_topic_score_gemma":0.003728683,"domain_scores_codex":[0.9986519,0.0003967151,0.00008287305,0.0003713459,0.0003903224,0.0001068491],"domain_scores_gemma":[0.9962376,0.001846917,0.0003696989,0.0009805749,0.0004360093,0.0001292329],"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":[0.0003602556,0.0003515501,0.008338969,0.0003529087,0.0001233201,0.0003633108,0.0005024066,0.5449536,0.07068791,0.006548916,0.004861022,0.3625559],"study_design_scores_gemma":[0.00001938116,0.0001424904,0.0004985775,0.00003063869,0.00002111524,0.00008973372,0.00004153242,0.9705788,0.01973449,0.005195332,0.003626006,0.00002192925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2058773,0.001402599,0.7609706,0.001679882,0.0002534595,0.0001779746,0.0002923679,0.02615637,0.003189485],"genre_scores_gemma":[0.7565336,0.0004153366,0.2366382,0.0009351372,0.00007494829,0.0001953336,0.0007608033,0.001690952,0.002755672],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00324369,"threshold_uncertainty_score":0.00897944,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04922846117780114,"score_gpt":0.323486207207921,"score_spread":0.2742577460301198,"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."}}