{"id":"W4404284707","doi":"10.36227/techrxiv.173144803.35072777/v1","title":"Adaptive Continuous Adversarial Training (ACAT) to Enhance ML-NIDS Robustness","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Robustness (evolution); Adversarial system; Computer science; Training (meteorology); Training set; Artificial intelligence; Machine learning; Chemistry; Geography; Biochemistry","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":[0.002331689,0.0009496387,0.0008895014,0.0004738182,0.0003888794,0.0006324105,0.001328818,0.0009259321,0.001557716],"category_scores_gemma":[0.01073403,0.0003057999,0.0005702429,0.0002778571,0.001221124,0.001389568,0.001793101,0.002161968,0.0004363286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005302307,"about_ca_system_score_gemma":0.0007100881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001293816,"about_ca_topic_score_gemma":0.001073012,"domain_scores_codex":[0.9985422,0.0004809733,0.00008146156,0.0003046838,0.000437278,0.0001534705],"domain_scores_gemma":[0.9947563,0.003227573,0.0004002877,0.0008829249,0.0005776056,0.000155159],"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":[0.0002726509,0.000143726,0.002507709,0.0001030316,0.00008267549,0.0001752953,0.0001241992,0.8488176,0.01463116,0.00976791,0.0021276,0.1212464],"study_design_scores_gemma":[0.000005006889,0.00003858197,0.000140167,0.000003623523,0.000005058059,0.00004465964,0.000004449857,0.9955402,0.002419549,0.001404356,0.0003893957,0.000004922904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03264072,0.0003379299,0.9629838,0.000299493,0.0001063866,0.00006830556,0.00003671143,0.001536035,0.001990624],"genre_scores_gemma":[0.8876798,0.0001429391,0.1097897,0.0003296818,0.00008794497,0.00008266575,0.0000885483,0.0001177122,0.001681063],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002331689,"threshold_uncertainty_score":0.01233131,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01439223001962434,"score_gpt":0.2497866799590729,"score_spread":0.2353944499394486,"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."}}