{"id":"W3154647937","doi":"10.1117/12.2585173","title":"Autonomous network cyber offence strategy through deep reinforcement learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Reinforcement learning; Computer science; Robustness (evolution); Artificial intelligence; Domain (mathematical analysis); Computer security","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001365707,0.0001464405,0.0001492704,0.00002391177,0.0002086798,0.0001571777,0.0004232884,0.00006623289,0.0002647251],"category_scores_gemma":[0.00004430825,0.0001451663,0.00006072982,0.0005044042,0.00003052471,0.0008346726,0.0003995606,0.0002460844,0.00008468099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008797077,"about_ca_system_score_gemma":0.00009909739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003280044,"about_ca_topic_score_gemma":0.00002912616,"domain_scores_codex":[0.9986405,0.00006141122,0.0002603953,0.0004397283,0.00022307,0.000374884],"domain_scores_gemma":[0.9990922,0.00006796823,0.00009793023,0.0005310638,0.0001484477,0.00006241973],"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":[0.000002812112,0.00002006656,0.00007034864,0.000008636633,0.00001696563,0.0000901882,0.000253064,0.6076607,0.0008502341,0.2899866,0.001077894,0.09996249],"study_design_scores_gemma":[0.0004099809,0.0004468178,0.0004367711,0.00005445861,0.00000987425,0.0002320687,0.0002046445,0.5597402,0.1950554,0.08752385,0.1549928,0.0008930956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001746603,0.0001629749,0.9398751,0.0002000024,0.0002248654,0.00009972652,3.380194e-8,0.001265446,0.05799716],"genre_scores_gemma":[0.5465345,0.00008597841,0.4436683,0.0008971084,0.00009851193,0.00003403717,0.000002495907,0.00001260499,0.008666505],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5463598,"threshold_uncertainty_score":0.5919708,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01811257081527174,"score_gpt":0.2637725179767449,"score_spread":0.2456599471614732,"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."}}