{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003078519,0.001486239,0.0005354283,0.002496697,0.0004435088,0.001768861,0.002020135,0.001165951,0.004075819],"category_scores_gemma":[0.01505104,0.000749324,0.001739043,0.0006269633,0.00132916,0.002527026,0.002438688,0.001665344,0.001836861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001257072,"about_ca_system_score_gemma":0.002174869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005835973,"about_ca_topic_score_gemma":0.006721509,"domain_scores_codex":[0.9961963,0.001403397,0.000306963,0.0005882391,0.001201115,0.0003040541],"domain_scores_gemma":[0.993176,0.003703882,0.0005295764,0.001468248,0.0009420582,0.0001801777],"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":[0.0005213725,0.0004791566,0.01284422,0.0008512422,0.0001776283,0.001442256,0.001442653,0.2139255,0.05925509,0.0326406,0.02314791,0.6532723],"study_design_scores_gemma":[0.00008741872,0.0002473657,0.0009804247,0.0001117597,0.00005132557,0.0005076016,0.0001380233,0.9055259,0.04621851,0.02608612,0.01996813,0.00007742913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01677927,0.0001453993,0.910858,0.0002714624,0.00004265596,0.0003037354,0.0005295154,0.06952894,0.001540939],"genre_scores_gemma":[0.2221899,0.0001421717,0.7666644,0.000293096,0.00002507782,0.0004054841,0.002967651,0.005822943,0.001489146],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005835973,"threshold_uncertainty_score":0.01628095,"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."}}