{"id":"W4206360774","doi":"10.1109/mcom.009.2100389","title":"ATMoS+: Generalizable Threat Mitigation in SDN Using Permutation Equivariant and Invariant Deep Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"IEEE Communications Magazine","topic":"Software-Defined Networks and 5G","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Reinforcement learning; Scalability; Invariant (physics); Distributed computing; Equivariant map; Software-defined networking; Set (abstract data type); Software; Network architecture; Permutation (music); Artificial intelligence; Theoretical computer science; Computer network; Operating 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":[0.0007959779,0.0005889022,0.0004639363,0.0001929977,0.0002336782,0.0004742119,0.00101885,0.0005131226,0.00122065],"category_scores_gemma":[0.001841918,0.0002404913,0.0003512451,0.0001491775,0.0007659449,0.0007843557,0.001006563,0.001115432,0.0001581953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007385226,"about_ca_system_score_gemma":0.001171645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005305716,"about_ca_topic_score_gemma":0.005614334,"domain_scores_codex":[0.9997827,0.00006358823,0.00001032831,0.0000551199,0.00004993692,0.00003826435],"domain_scores_gemma":[0.9995713,0.0001933597,0.00005575151,0.00006437076,0.0000677377,0.00004756077],"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":[0.00004551271,0.0000318172,0.0006238387,0.0000168715,0.00001894569,0.00002786443,0.000016949,0.9714779,0.001361397,0.005071157,0.0005477667,0.02075996],"study_design_scores_gemma":[0.000003238225,0.00001023248,0.00002475996,7.014254e-7,0.000001074478,0.000001860686,8.563094e-7,0.9983053,0.0001854999,0.001385922,0.00007961999,9.099419e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07166273,0.0001374214,0.923524,0.0002729084,0.00006412956,0.0000540025,0.00006434863,0.001621854,0.002598769],"genre_scores_gemma":[0.9256884,0.00007261281,0.07221901,0.0001183569,0.00001981129,0.00005911379,0.00008678075,0.00007459881,0.001661245],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005305716,"threshold_uncertainty_score":0.01054966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04306211764270063,"score_gpt":0.2847231214594093,"score_spread":0.2416610038167087,"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."}}