{"id":"W3086579950","doi":"10.1109/tii.2020.3023430","title":"DeepFed: Federated Deep Learning for Intrusion Detection in Industrial Cyber–Physical Systems","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Informatics","topic":"Smart Grid Security and Resilience","field":"Engineering","cited_by":568,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"Fundamental Research Funds for the Central Universities; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Computer science; Deep learning; Intrusion detection system; Cyber-physical system; Computer security; Artificial intelligence; Paillier cryptosystem; Industrial control system; Convolutional neural network; Distributed computing; Machine learning; Cryptosystem; Cryptography","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":[0.001472734,0.0009788419,0.000757934,0.0007121395,0.0004196453,0.000753346,0.001727212,0.00125197,0.001198504],"category_scores_gemma":[0.002464317,0.0003500861,0.0006358511,0.0005684713,0.0007142199,0.00175997,0.001757299,0.001516926,0.0002701238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001200331,"about_ca_system_score_gemma":0.001516556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00643931,"about_ca_topic_score_gemma":0.007620247,"domain_scores_codex":[0.9994612,0.0001383261,0.0000361464,0.0001342062,0.0001292804,0.0001009073],"domain_scores_gemma":[0.9994065,0.0002061103,0.00008054906,0.0001296582,0.0001309227,0.00004630955],"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":[0.0002658003,0.0003112785,0.004596419,0.00011803,0.0001554302,0.0001589034,0.00008112848,0.7079529,0.00583607,0.006680787,0.004862464,0.2689808],"study_design_scores_gemma":[0.000005488282,0.00002390743,0.0001168975,0.000003894767,0.000004886209,0.00001127749,0.000003659438,0.9962257,0.00119466,0.002151727,0.0002545164,0.000003370059],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07485817,0.000956609,0.9167523,0.0005510275,0.00009242013,0.00007499815,0.000302044,0.004917003,0.00149535],"genre_scores_gemma":[0.8635874,0.0002823208,0.1322682,0.0004060122,0.00003270133,0.0001065483,0.0007164434,0.00007738991,0.00252293],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00643931,"threshold_uncertainty_score":0.01280361,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03550043727804655,"score_gpt":0.2297796029021805,"score_spread":0.1942791656241339,"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."}}