{"id":"W4313005202","doi":"10.1109/access.2022.3228507","title":"Evaluation of Synthetic Data Generation Techniques in the Domain of Anonymous Traffic Classification","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Internet Traffic Analysis and Secure E-voting","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Autoencoder; Boosting (machine learning); Traffic classification; Synthetic data; Deep learning; Data mining; Network packet; Computer network","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":[0.005867566,0.00006110351,0.0001167197,0.0001520135,0.0000735698,0.0000705178,0.002362296,0.00002277837,0.00002567891],"category_scores_gemma":[0.00005708781,0.00004826608,0.0000331765,0.0005575284,0.00002683353,0.0004431192,0.0001920276,0.0001016357,4.596038e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005592398,"about_ca_system_score_gemma":0.00009508211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002583072,"about_ca_topic_score_gemma":0.0001596645,"domain_scores_codex":[0.9976307,0.0007623726,0.0003600233,0.0002791355,0.0008805088,0.00008723965],"domain_scores_gemma":[0.9988739,0.00007239226,0.0002613754,0.0006133012,0.0001712235,0.000007782433],"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":[0.00001587807,0.0009176845,0.0002062136,0.00004399669,0.00008285621,0.00000493693,0.01229388,0.3471829,0.02127605,0.07723536,0.003789615,0.5369506],"study_design_scores_gemma":[0.00008562052,0.00003314111,0.0003187292,0.000006973308,0.000029839,0.000003740098,0.0002203505,0.9965349,0.002524362,0.0001087761,0.00008249793,0.00005099753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.750122,0.00008124432,0.2487937,0.0002936413,0.0001320573,0.0002599042,0.000006172925,0.00002029325,0.0002909276],"genre_scores_gemma":[0.9987047,0.000004183665,0.001114263,0.00004647913,0.00003997269,0.0000542932,0.00002990962,0.000003537899,0.000002701571],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6493521,"threshold_uncertainty_score":0.4389773,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1449064349790307,"score_gpt":0.3603137582957061,"score_spread":0.2154073233166753,"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."}}