{"id":"W4414518972","doi":"10.1016/j.comnet.2025.111739","title":"Adversarial attack and defence of federated learning-based network traffic classification in edge computing environment","year":2025,"lang":"en","type":"article","venue":"Computer Networks","topic":"Internet Traffic Analysis and Secure E-voting","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"University of Waterloo; Universiti Malaya; Ministry of Higher Education, Malaysia","keywords":"Backdoor; Adversarial system; Scalability; Enhanced Data Rates for GSM Evolution; Attack surface; Class (philosophy); Attack model; Edge device; Security domain","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006251319,0.0002075386,0.0003698278,0.0001406783,0.0001741028,0.0001574795,0.0004686818,0.0001448167,0.000004310099],"category_scores_gemma":[0.00001066073,0.0002121186,0.00009426368,0.0005637624,0.00008660468,0.0001148213,0.0002725943,0.0003956541,0.000002988293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006994739,"about_ca_system_score_gemma":0.00005212624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004646431,"about_ca_topic_score_gemma":0.00002181744,"domain_scores_codex":[0.9980322,0.0002715338,0.000573899,0.0005697044,0.0001736703,0.0003790587],"domain_scores_gemma":[0.9991324,0.0003259096,0.0002362656,0.0001968429,0.00005027621,0.0000583122],"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":[0.00001342555,0.00005567594,0.001829633,0.00001493358,0.00002807648,0.000004509633,0.0001756087,0.9295686,0.000001721887,0.005684964,0.0005249974,0.06209788],"study_design_scores_gemma":[0.0005908842,0.00007179008,0.008113905,0.0001970401,0.00001488406,0.000001355566,0.00001426256,0.9902245,0.000003204027,0.000005413259,0.0005920729,0.0001707021],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09752735,0.0003887473,0.9011341,0.0001373541,0.0004899617,0.000154401,1.302521e-7,0.00008034104,0.00008765372],"genre_scores_gemma":[0.9846843,0.0000195682,0.01481679,0.0002131646,0.0002183881,0.000003558645,0.0000119052,0.000008320873,0.00002394147],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.887157,"threshold_uncertainty_score":0.8649943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0130989551911627,"score_gpt":0.2304691209984866,"score_spread":0.2173701658073239,"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."}}