{"id":"W4402352815","doi":"10.1109/ijcnn60899.2024.10650368","title":"Knowledge-Informed Auto-Penetration Testing Based on Reinforcement Learning with Reward Machine","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University","keywords":"Reinforcement learning; Computer science; Penetration (warfare); Machine learning; Artificial intelligence; Reinforcement; Psychology; Engineering; Social psychology; Operations research","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004592133,0.0001710814,0.0001140187,0.0002458995,0.000176724,0.0004212385,0.0003294149,0.00004592235,0.00001931041],"category_scores_gemma":[0.0007576273,0.0001228187,0.00003288253,0.0007753488,0.00002208014,0.0003155014,0.00007889628,0.0002521951,0.00008073561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001173917,"about_ca_system_score_gemma":0.0003111453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000875791,"about_ca_topic_score_gemma":0.00001113651,"domain_scores_codex":[0.9988606,0.00003562614,0.0002125673,0.0003548739,0.0002853337,0.0002510304],"domain_scores_gemma":[0.9982196,0.001207883,0.00004918514,0.0003547035,0.00009604965,0.00007259751],"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":[0.00004355229,0.0001211628,0.0150321,0.0004803462,0.00004615621,0.0001430165,0.001622007,0.176213,0.0002437196,0.02452387,0.02524928,0.7562817],"study_design_scores_gemma":[0.0001031918,0.0007384517,0.0005347363,0.0006128965,0.000005100354,0.00001737337,0.00000188106,0.9936519,0.0007123777,0.000689031,0.002740117,0.0001929577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002825249,0.00004492421,0.9131145,0.0003127863,0.0001225845,0.0001455772,1.296503e-7,0.02448801,0.06148891],"genre_scores_gemma":[0.7073455,8.305037e-7,0.2910987,0.0002182174,0.00003552105,0.00002582492,0.000004627736,0.00001281546,0.001257958],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8174388,"threshold_uncertainty_score":0.5008403,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03125521645134659,"score_gpt":0.28878440336497,"score_spread":0.2575291869136234,"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."}}