{"id":"W4399333297","doi":"10.1016/j.egyai.2024.100381","title":"Evasive attacks against autoencoder-based cyberattack detection systems in power systems","year":2024,"lang":"en","type":"article","venue":"Energy and AI","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; University of Toronto","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Autoencoder; Adversarial system; Computer science; Robustness (evolution); Computer security; Smart grid; Threat model; Adversarial machine learning; Deep learning; Situation awareness; Artificial intelligence; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003294676,0.0001652666,0.0001841596,0.0002236195,0.0001303988,0.0004934707,0.0002508858,0.0001234764,0.00000320166],"category_scores_gemma":[0.00004058836,0.0001498378,0.00004140973,0.0004488478,0.00003344028,0.0004634408,0.00009348945,0.0002556413,0.00001162672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001003044,"about_ca_system_score_gemma":0.00009094381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004072081,"about_ca_topic_score_gemma":0.00008267644,"domain_scores_codex":[0.998637,0.0002104238,0.0002373408,0.0004543109,0.000212427,0.0002485499],"domain_scores_gemma":[0.9994076,0.00017024,0.00004929222,0.0002636862,0.00004054318,0.00006859296],"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":[0.000004903098,0.00001344401,0.0001459026,0.00006123193,0.00001547641,0.0001399437,0.000258128,0.9539169,0.0004209556,0.03969079,0.0002093081,0.005123011],"study_design_scores_gemma":[0.0001982459,0.00004720986,0.0001405755,0.0002563758,0.000003670744,0.00001887449,0.00004876166,0.975882,0.0002128963,0.00009059923,0.02292097,0.0001798357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01067788,0.002408918,0.9811851,0.0003497485,0.003167727,0.00008525649,0.000001375996,0.0003062374,0.001817806],"genre_scores_gemma":[0.9985759,0.00001777755,0.0005067231,0.0001914723,0.0001268401,0.00003227167,0.000003271106,0.0000164277,0.000529315],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9878981,"threshold_uncertainty_score":0.6110208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007464424445712928,"score_gpt":0.2460430600922725,"score_spread":0.2385786356465595,"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."}}