{"id":"W6995718057","doi":"","title":"Pioneering Autonomous Penetration Testing with Large Language Models through Prompt Engineering and Agentic System Design","year":2025,"lang":"en","type":"dissertation","venue":"QSpace (Queen's University Library)","topic":"Cancer Cells and Metastasis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Offensive; Adaptability; Flexibility (engineering); Adversary; Viable system model; Systems design; Ontology; Cyber-physical system","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":[0.002031304,0.0007571569,0.0003408497,0.0005283192,0.0005075676,0.001868606,0.0009894525,0.0007923756,0.002492486],"category_scores_gemma":[0.00626995,0.0003979894,0.0007994088,0.0002707663,0.002923717,0.002455606,0.001704615,0.00225839,0.000575067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001165412,"about_ca_system_score_gemma":0.001793418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001143698,"about_ca_topic_score_gemma":0.001438305,"domain_scores_codex":[0.9986876,0.0005705355,0.00005770155,0.0001947385,0.0004004033,0.00008907245],"domain_scores_gemma":[0.996695,0.002066357,0.0002487923,0.0004478513,0.0004225066,0.0001194779],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000138698,0.0002637272,0.001738666,0.0006450142,0.00007194644,0.000243184,0.003353788,0.1465353,0.06061297,0.4903805,0.003507669,0.2925086],"study_design_scores_gemma":[0.00009632845,0.0008271685,0.0006175386,0.000242054,0.00007394857,0.0003127487,0.0006909354,0.6002668,0.07877205,0.2350016,0.08300231,0.00009658942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01192876,0.0002532728,0.9810538,0.0004430391,0.00004811105,0.0001342281,0.00002166972,0.0006414849,0.005475657],"genre_scores_gemma":[0.2843593,0.0007245873,0.7082348,0.0002792435,0.00003564524,0.0002954564,0.00008129195,0.0002326129,0.005757054],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002492486,"threshold_uncertainty_score":0.01074272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01235019842549172,"score_gpt":0.195665895714838,"score_spread":0.1833156972893462,"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."}}