{"id":"W4399115146","doi":"10.48550/arxiv.2405.15908","title":"Knowledge-Informed Auto-Penetration Testing Based on Reinforcement Learning with Reward Machine","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University","keywords":"Reinforcement learning; Penetration (warfare); Reinforcement; Artificial intelligence; Computer science; Machine learning; Psychology; Social psychology; Engineering; Operations research","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":[0.001987915,0.001130008,0.001452311,0.0006056221,0.0004488965,0.0008000291,0.001833504,0.001261488,0.001900792],"category_scores_gemma":[0.009224445,0.0005943103,0.0006342626,0.0003940948,0.001536159,0.001683889,0.001710811,0.001855778,0.0002820712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001124866,"about_ca_system_score_gemma":0.002183864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005077584,"about_ca_topic_score_gemma":0.003683264,"domain_scores_codex":[0.9985525,0.0005441499,0.00006849017,0.0003298306,0.0002616915,0.0002433992],"domain_scores_gemma":[0.9938374,0.004121376,0.0006904146,0.0004891845,0.0005652028,0.0002962636],"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":[0.0000892147,0.00006995093,0.001426295,0.00004253255,0.000024957,0.00008858232,0.00004861115,0.9530482,0.001141571,0.004999068,0.0005349782,0.03848602],"study_design_scores_gemma":[0.000007297611,0.00002455369,0.00006124069,0.000003106938,0.000003047864,0.000009130761,0.000002890664,0.9976666,0.0003896185,0.001757686,0.00007193944,0.00000291591],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07269918,0.0002080471,0.9224527,0.0004150849,0.00003646278,0.0001009387,0.00006930865,0.001908982,0.002109315],"genre_scores_gemma":[0.9491504,0.00005324636,0.04962859,0.0001364772,0.00001286055,0.0000960683,0.00006971323,0.00006440292,0.0007881924],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005077584,"threshold_uncertainty_score":0.01051325,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05516487002473297,"score_gpt":0.2011951126820938,"score_spread":0.1460302426573608,"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."}}