{"id":"W4409075946","doi":"10.1007/978-3-031-82362-6_5","title":"Deep Learning for Network Anomaly Detection Under Data Contamination: Evaluating Robustness and Mitigating Performance Degradation","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Robustness (evolution); Anomaly detection; Contamination; Degradation (telecommunications); Artificial intelligence; Data mining; Real-time computing; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001542235,0.0003122998,0.0003000491,0.000360667,0.0010264,0.0005134188,0.001510237,0.000235165,0.000002731192],"category_scores_gemma":[0.0001378236,0.0003270892,0.00004642893,0.0006284007,0.0002324817,0.00093676,0.001099758,0.0005281151,9.761741e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002075288,"about_ca_system_score_gemma":0.0002216318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001147567,"about_ca_topic_score_gemma":0.0001094208,"domain_scores_codex":[0.9973605,0.00003653332,0.0004740021,0.001325185,0.000416694,0.0003870747],"domain_scores_gemma":[0.9975548,0.0006726672,0.0004031156,0.0009364123,0.0003657622,0.00006720916],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002541917,0.000003856179,0.0000567779,0.0000417352,0.000005185773,3.395953e-7,0.00003933001,0.2109895,0.00006377812,0.004187895,0.000002157426,0.7846069],"study_design_scores_gemma":[0.0001715044,0.0001714751,0.000497041,0.0002869336,0.00001761141,0.00002227798,6.741952e-7,0.9852169,0.0008344855,0.0121525,0.0002978122,0.0003307407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006828972,0.0003182996,0.9970222,0.0002688542,0.0004239784,0.0007194096,0.000001798196,0.0002310952,0.0003315067],"genre_scores_gemma":[0.3013712,0.00006625253,0.6975555,0.0002394609,0.0003209026,0.00007167979,0.00003281903,0.00001925261,0.0003229595],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7842762,"threshold_uncertainty_score":0.9999181,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03443495595358669,"score_gpt":0.289236039674537,"score_spread":0.2548010837209503,"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."}}