{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003394579,0.001215406,0.0007463493,0.0009521972,0.0005408151,0.0007620971,0.001233228,0.001222093,0.0007066335],"category_scores_gemma":[0.008554354,0.0002100693,0.0006437215,0.0006669549,0.0009381693,0.001036827,0.0008665493,0.00149495,0.0004938613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000966303,"about_ca_system_score_gemma":0.0007254785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006819956,"about_ca_topic_score_gemma":0.005946095,"domain_scores_codex":[0.998278,0.0007024455,0.00008783563,0.0003307284,0.0004315689,0.0001693628],"domain_scores_gemma":[0.9952218,0.002585697,0.0002773319,0.0006333925,0.001028751,0.0002530434],"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":[0.001192478,0.001561241,0.02130903,0.0004245043,0.0002166277,0.0003728694,0.0002397107,0.8040301,0.01001183,0.003932654,0.01306308,0.1436459],"study_design_scores_gemma":[0.00003350459,0.0002193362,0.00281478,0.00002984371,0.00001532776,0.00008463482,0.00008432054,0.9871055,0.006590248,0.001177333,0.001827483,0.00001773966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.903971,0.001525586,0.08053807,0.001264995,0.0006098778,0.0004095143,0.002779779,0.002960335,0.005940769],"genre_scores_gemma":[0.9550747,0.0003020767,0.03625929,0.0003426469,0.00008287945,0.000160634,0.005945179,0.0001232266,0.001709421],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006819956,"threshold_uncertainty_score":0.01795244,"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."}}