{"id":"W4382119126","doi":"10.1109/jsyst.2023.3286375","title":"A Generalizable Deep Neural Network Method for Detecting Attacks in Industrial Cyber-Physical Systems","year":2023,"lang":"en","type":"article","venue":"IEEE Systems Journal","topic":"Smart Grid Security and Resilience","field":"Engineering","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; University of Guelph","funders":"","keywords":"Computer science; Cyber-physical system; Robustness (evolution); Artificial neural network; Electric power system; Artificial intelligence; Data mining; Machine learning; Deep learning; Regularization (linguistics); Data modeling; Power (physics); Database","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":[0.001661967,0.0002386819,0.0005115922,0.0002338022,0.000278515,0.0002743602,0.0002849291,0.0002314523,0.000001701192],"category_scores_gemma":[0.00008777426,0.0002146347,0.000168857,0.0007986391,0.00001927724,0.0002219669,0.00002442402,0.0007738718,0.00002262829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001731676,"about_ca_system_score_gemma":0.00003834224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000140443,"about_ca_topic_score_gemma":0.00005867989,"domain_scores_codex":[0.9976578,0.000301466,0.0006363543,0.0002284502,0.0003398959,0.0008360469],"domain_scores_gemma":[0.9989939,0.0004287393,0.0001321386,0.0001803055,0.00007023248,0.0001947126],"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":[0.0000189056,0.000008754886,0.000714585,0.0001190271,0.00005040714,0.00007545223,0.000594379,0.9902706,0.001664122,0.00003734032,0.00565694,0.0007895143],"study_design_scores_gemma":[0.0008344026,0.00006412019,0.00009034248,0.0002448873,0.00002029756,0.0005217922,0.0003586344,0.993391,0.0001961886,0.00004482413,0.00398135,0.0002521966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8609797,0.001293929,0.1082812,0.00003073705,0.02818824,0.0007231822,0.00001055823,0.0003381063,0.0001543482],"genre_scores_gemma":[0.9846373,0.00002909462,0.0003637997,0.000008396613,0.01470055,0.0001055081,0.000002774319,0.000062452,0.00009012021],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1236576,"threshold_uncertainty_score":0.8752549,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04387600120949124,"score_gpt":0.2925961545763883,"score_spread":0.2487201533668971,"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."}}