{"id":"W7034200459","doi":"","title":"STAF : Leveraging LLMs for Automated AttackTree-Based Security Test Generation","year":2024,"lang":"en","type":"article","venue":"DiVA (Mälardalen University College)","topic":"Libraries, Manuscripts, and Books","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; HORIZON EUROPE Framework Programme; European Commission","keywords":"Automotive industry; Executable; Automation; Security testing; Test (biology); Test case","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001599188,0.000236918,0.00023665,0.0002692436,0.0009835117,0.0004404039,0.0002692861,0.0000935034,0.0009762343],"category_scores_gemma":[0.00002626953,0.0002483538,0.0001936986,0.0001093518,0.0002140929,0.0009039264,0.00008440889,0.0001571335,0.00008412114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001872826,"about_ca_system_score_gemma":0.0002972912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00031283,"about_ca_topic_score_gemma":0.001091269,"domain_scores_codex":[0.9987566,0.00005591233,0.0001846836,0.0004284958,0.0002298058,0.0003445213],"domain_scores_gemma":[0.9992226,0.0002073197,0.00005695631,0.0002372276,0.0001731606,0.0001027136],"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":[0.0000894639,0.0001666484,0.0003068177,0.0003550636,0.0001529647,0.0001895206,0.01263815,0.00008667626,0.0002419175,0.4690139,0.5163289,0.0004299862],"study_design_scores_gemma":[0.0008512038,0.00012365,0.00006365043,0.00006700053,0.0001127658,0.000001754432,0.003244214,0.1600213,0.0004983414,0.0007481378,0.8339253,0.0003426675],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6870834,0.001411957,0.005839378,0.01429684,0.01090795,0.004325639,0.02665869,0.01117102,0.2383052],"genre_scores_gemma":[0.9161916,0.000007255504,0.000236805,0.0004079559,0.0008648371,0.000004220407,0.0003762709,0.00003546266,0.08187553],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4682658,"threshold_uncertainty_score":0.9999969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1431627912711303,"score_gpt":0.2106269462502189,"score_spread":0.06746415497908856,"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."}}