{"id":"W3010162966","doi":"10.23919/cnsm46954.2019.9012662","title":"A Framework & System for Classification of Encrypted Network Traffic using Machine Learning","year":2019,"lang":"en","type":"article","venue":"","topic":"Internet Traffic Analysis and Secure E-voting","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Solana Networks (Canada)","funders":"","keywords":"Traffic classification; Computer science; Artificial intelligence; Encryption; Deep packet inspection; Machine learning; Binary classification; Software deployment; Traffic generation model; Support vector machine; Identification (biology); Network packet; Ground truth; Data mining; Real-time computing; 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":[0.001093805,0.0009551835,0.0008706466,0.001779951,0.0007535348,0.00168387,0.002453547,0.001265936,0.01111701],"category_scores_gemma":[0.002690537,0.0005157298,0.0005803505,0.000817542,0.0005234149,0.002127715,0.001439085,0.001341411,0.007360636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001077568,"about_ca_system_score_gemma":0.001449644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004688088,"about_ca_topic_score_gemma":0.004044113,"domain_scores_codex":[0.9993305,0.00006777392,0.00004577777,0.0002389433,0.0002490674,0.0000679762],"domain_scores_gemma":[0.9992023,0.0001483628,0.00007336761,0.0001852232,0.0003200876,0.00007067964],"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":[0.0009669756,0.001094075,0.005826937,0.0002850963,0.0002229938,0.0004888871,0.0002014282,0.04899398,0.05354449,0.01394627,0.07725368,0.7971752],"study_design_scores_gemma":[0.00007108204,0.0001849816,0.001290036,0.00002865258,0.00002989369,0.0002305878,0.00003127632,0.9363372,0.03538668,0.006185299,0.02016583,0.00005850016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01257134,0.0001503191,0.8596376,0.0002969574,0.000167609,0.0005570724,0.001294793,0.1214961,0.003828224],"genre_scores_gemma":[0.2127638,0.000176347,0.7693114,0.0004291131,0.0001112677,0.0008729417,0.004357292,0.001333973,0.01064389],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01111701,"threshold_uncertainty_score":0.03719008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03094149336751063,"score_gpt":0.2680108568899983,"score_spread":0.2370693635224876,"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."}}