{"id":"W4416509201","doi":"10.1016/j.eswa.2025.130460","title":"Explainable resource-Aware IoT security model via knowledge distillation and adaptive loss function optimization","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Divergence (linguistics); Convergence (economics); Artificial neural network; Convolutional neural network; Feature (linguistics); Distillation; Memory footprint; Compiler; Internet of Things","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":[],"consensus_categories":[],"category_scores_codex":[0.0002037149,0.0001820404,0.0001853649,0.0001834027,0.0006952914,0.0001775863,0.0002410431,0.0001323443,0.000003347773],"category_scores_gemma":[0.000006098236,0.0001664583,0.00002988622,0.0008700759,0.00006772169,0.000376892,0.0001262768,0.0001421144,0.000009659636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001433895,"about_ca_system_score_gemma":0.00007546126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009251646,"about_ca_topic_score_gemma":0.00003485248,"domain_scores_codex":[0.9986825,0.00009717617,0.0002878394,0.0005462375,0.0001761447,0.0002100809],"domain_scores_gemma":[0.9989028,0.0000756596,0.0001427267,0.0005365964,0.0002522963,0.00008992284],"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":[0.0001175965,0.0002017229,0.00008660358,0.0001137657,0.00006137437,8.803479e-7,0.002877919,0.6888868,0.0001060402,0.2873422,0.004750156,0.01545491],"study_design_scores_gemma":[0.0002776461,0.00006749999,0.00003102015,0.00007752996,0.00001105194,0.00001145072,0.0002421296,0.9649971,0.00008090674,0.002315135,0.03171282,0.0001756999],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004305773,0.001564098,0.9924998,0.0002591682,0.0001372723,0.001013461,0.000004551768,0.0003084353,0.003782592],"genre_scores_gemma":[0.988983,0.0000598318,0.008671902,0.00008611676,0.000155498,0.001387838,0.00002611177,0.00001386979,0.0006157944],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9885525,"threshold_uncertainty_score":0.6787974,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008705002824890227,"score_gpt":0.2280927523612525,"score_spread":0.2193877495363623,"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."}}