{"id":"W4297825308","doi":"10.3390/jsan11030045","title":"Adversarial Attacks on Heterogeneous Multi-Agent Deep Reinforcement Learning System with Time-Delayed Data Transmission","year":2022,"lang":"en","type":"article","venue":"Journal of Sensor and Actuator Networks","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Reinforcement learning; Robustness (evolution); Transmission (telecommunications); Adversarial system; Cluster (spacecraft); Data transmission; Artificial intelligence; Distributed computing; Computer network; Telecommunications","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":[0.0009335974,0.000250412,0.0003931136,0.0001473316,0.0006934199,0.0001434873,0.001031308,0.00007198076,0.00005457687],"category_scores_gemma":[0.00002589478,0.000193876,0.00008892207,0.0002198234,0.00003774396,0.0003976495,0.0005517844,0.001149765,0.000003363996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001857803,"about_ca_system_score_gemma":0.00007022765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001007226,"about_ca_topic_score_gemma":6.067764e-7,"domain_scores_codex":[0.9975456,0.0003852966,0.0005476944,0.0003988733,0.0007683712,0.0003541634],"domain_scores_gemma":[0.9983238,0.0002150543,0.0006830415,0.0004636179,0.00008314445,0.000231365],"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":[0.0005934758,0.00004561443,0.00005467578,0.00001291888,0.0001330251,0.0004269374,0.0005195101,0.9775267,0.0000786117,0.00003407656,0.0001233468,0.02045107],"study_design_scores_gemma":[0.00202275,0.001238169,0.00003327085,0.0000887241,0.00006858845,0.000916191,0.000264643,0.9901298,0.00002163072,0.00000109666,0.004988038,0.0002270405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01349151,0.0002257415,0.985272,0.0001777158,0.0005159289,0.0001827106,0.000001234017,0.00006515133,0.00006798506],"genre_scores_gemma":[0.974626,0.00004485982,0.02461677,0.0001341096,0.0004193928,0.000002381155,0.00001269536,0.00003087602,0.0001129358],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9611345,"threshold_uncertainty_score":0.7906035,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01645218397278949,"score_gpt":0.245728690659178,"score_spread":0.2292765066863885,"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."}}