{"id":"W7117891992","doi":"10.1109/milcom64451.2025.11310014","title":"Detecting Stealthy Anomalies with Autoencoders Using Windowed Variance-Aware Loss Functions","year":2025,"lang":"","type":"article","venue":"","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Autoencoder; Intrusion detection system; Pattern recognition (psychology); Enhanced Data Rates for GSM Evolution; Intrusion; Skew; Artificial neural network","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001684729,0.001238758,0.0008716463,0.0008871006,0.0002431273,0.0007524416,0.0007377072,0.0007928749,0.0006950192],"category_scores_gemma":[0.004211572,0.0003929253,0.0006457203,0.0004446813,0.0006214308,0.001400093,0.0009005193,0.001459922,0.0003520004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005690164,"about_ca_system_score_gemma":0.0006775296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002697622,"about_ca_topic_score_gemma":0.003428419,"domain_scores_codex":[0.9994468,0.0001204971,0.0000408962,0.0001467905,0.0001759183,0.00006904635],"domain_scores_gemma":[0.997797,0.001263249,0.000261367,0.0002515814,0.0003737393,0.00005307842],"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":[0.0003696967,0.0002447541,0.007842315,0.00008594849,0.0001531093,0.0002041566,0.00009776967,0.6643689,0.02522597,0.002974825,0.002216157,0.2962164],"study_design_scores_gemma":[0.00000405854,0.0000422328,0.0007589387,0.00000591002,0.000009867676,0.00004010903,0.000007702299,0.9941018,0.004164878,0.0006787775,0.0001791165,0.000006511061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1830291,0.0006138597,0.8123248,0.0003362925,0.00006546625,0.00005467313,0.0001586968,0.002120714,0.001296382],"genre_scores_gemma":[0.87371,0.000375971,0.1225387,0.0002004165,0.00005372718,0.00007318996,0.0004902891,0.000142746,0.002414973],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002697622,"threshold_uncertainty_score":0.008909762,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01762996024634406,"score_gpt":0.2509536693096415,"score_spread":0.2333237090632974,"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."}}